© 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. 15-RESID-POST-AA
    6. 116700
    Prev
    Next
    INDEX
    Explanations

    Math/logic problems

    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
    앝
    -0.07
    רוק
    -0.07
     require
    -0.06
    _Property
    -0.06
     crimes
    -0.06
    Strong
    -0.06
    obs
    -0.06
    reso
    -0.06
    _NODE
    -0.06
    (images
    -0.06
    POSITIVE LOGITS
    .Serve
    0.08
     gaz
    0.07
    fclose
    0.07
    ♕
    0.07
    icorn
    0.07
    崇拜
    0.06
    ){}↵
    0.06
    газ
    0.06
    ㄏ
    0.06
    );
    ↵
    ↵
    ↵
    0.06
    Activations Density 0.019%

    No Known Activations