© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 3442
    Prev
    Next
    INDEX
    Explanations

    affiliate

    np_max-act · gemini-2.0-flash

    content about affiliate marketing—particularly references to affiliate programs, networks, publishers/advertisers, and commission-based structures.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     władz
    -0.08
    ände
    -0.07
    纻
    -0.07
    大哥
    -0.07
     positivity
    -0.07
     MANAGEMENT
    -0.07
     paw
    -0.06
    傒
    -0.06
    右手
    -0.06
    /Admin
    -0.06
    POSITIVE LOGITS
    reffen
    0.08
    libs
    0.07
    _seconds
    0.06
    塞尔
    0.06
     transfers
    0.06
    沪
    0.06
    麻烦
    0.06
    䎖
    0.06
    squeeze
    0.06
     segreg
    0.06
    Activations Density 0.012%

    No Known Activations