© 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
    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. 24201
    Prev
    Next
    INDEX
    Explanations

    score

    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
     COMPUTER
    -0.09
    :on
    -0.08
    とする
    -0.07
    .generator
    -0.07
    SAFE
    -0.07
    Stroke
    -0.07
    /operator
    -0.07
    (Model
    -0.07
    _BOLD
    -0.07
    "s
    -0.07
    POSITIVE LOGITS
    疬
    0.07
    学会
    0.07
    �
    0.07
    댜
    0.07
     Calls
    0.06
    _cipher
    0.06
    شدد
    0.06
     urges
    0.06
    aeper
    0.06
    แบร
    0.06
    Activations Density 0.017%

    No Known Activations