© 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 EvalsExportsinterp-engineNEWAPI 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. 70661
    Prev
    Next
    INDEX
    Explanations

    hidden Unicode formatting/control characters embedded within words (e.g., zero-width joiners/non-joiners).

    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
     overcome
    -0.08
    邪恶
    -0.08
    本身就是
    -0.07
     dermat
    -0.07
     vascular
    -0.07
    👹
    -0.07
    太阳城
    -0.07
    增设
    -0.07
    越野
    -0.07
    늙
    -0.07
    POSITIVE LOGITS
    BUM
    0.07
    阿拉
    0.06
    쏨
    0.06
    安全事故
    0.06
    照
    0.06
     Cost
    0.06
    .Class
    0.06
     büt
    0.06
     Attention
    0.06
    >
↵
↵
    0.06
    Activations Density 0.023%

    No Known Activations