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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 130036
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    已经在
    -0.07
    <cv
    -0.07
    Laura
    -0.07
     processes
    -0.07
    إز
    -0.07
    SU
    -0.07
    克服
    -0.07
    Mac
    -0.07
    ARB
    -0.07
     Erf
    -0.07
    POSITIVE LOGITS
    ⼀
    0.08
    .*↵
    0.07
    =nil
    0.07
    _Select
    0.07
    parentId
    0.07
    能耗
    0.07
     Girlfriend
    0.07
     Qty
    0.06
    _VALUE
    0.06
    毛利率
    0.06
    Activations Density 0.004%

    No Known Activations