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

    Neuronpedia

    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. 49365
    Prev
    Next
    INDEX
    Explanations

    annex

    np_max-act · gemini-2.0-flash
    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
     prayed
    -0.07
    _cl
    -0.07
     ache
    -0.07
    剩
    -0.07
    -thinking
    -0.07
    -size
    -0.07
    constraint
    -0.06
    peng
    -0.06
    alleng
    -0.06
    _group
    -0.06
    POSITIVE LOGITS
    四
    0.08
    濋
    0.06
     Fifth
    0.06
    ichert
    0.06
    ⁘
    0.06
     Ottawa
    0.06
    一般都是
    0.06
     ...)
    0.06
    🔓
    0.06
    幺
    0.06
    Activations Density 0.011%

    No Known Activations