Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 22967
    Prev
    Next
    INDEX
    Explanations

    4

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Then
    -0.07
    uckle
    -0.07
    Martin
    -0.07
    芜湖
    -0.07
     utilize
    -0.07
    ul
    -0.07
    Ident
    -0.07
    .mipmap
    -0.07
     hold
    -0.07
    Further
    -0.06
    POSITIVE LOGITS
     каз
    0.07
    owość
    0.06
     initWithTitle
    0.06
    ":{↵
    0.06
    党政
    0.06
    /tinyos
    0.06
     سوريا
    0.06
     superficial
    0.06
     smokers
    0.06
    𬊤
    0.06
    Activations Density 0.004%

    No Known Activations