© 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. 45520
    Prev
    Next
    INDEX
    Explanations

    #

    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
    儿
    -0.07
    Scaling
    -0.07
     actions
    -0.07
    .sign
    -0.07
     Facility
    -0.07
     implant
    -0.07
    Guard
    -0.07
    _decision
    -0.06
    Figure
    -0.06
     Damian
    -0.06
    POSITIVE LOGITS
    +x
    0.07
    امج
    0.07
    wpdb
    0.07
    ಥ
    0.07
    ombine
    0.07
    排出
    0.07
    ทรา
    0.07
    一页
    0.07
    生活习惯
    0.06
    isle
    0.06
    Activations Density 0.001%

    No Known Activations