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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-RESID-POST-AA
    6. 31252
    Prev
    Next
    INDEX
    Explanations

    say "number 1 or 2"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reproductive
    -0.08
    💑
    -0.07
    entialAction
    -0.07
    させて頂
    -0.07
     Southwest
    -0.07
    .Dial
    -0.07
    "—
    -0.07
    ↵↵↵↵
    -0.07
     Organization
    -0.07
    人体
    -0.07
    POSITIVE LOGITS
     numberOf
    0.08
    enchmark
    0.07
    特殊情况
    0.07
     shields
    0.06
    税费
    0.06
    claims
    0.06
    Faces
    0.06
    uma
    0.06
    BarButton
    0.06
    -course
    0.06
    Activations Density 0.008%

    No Known Activations