© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 88899
    Prev
    Next
    INDEX
    Explanations

    Questions and/or subjective analyses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ỡ
    -0.27
    ä¹ŁæĹłæ³ķ
    -0.25
    ãģij
    -0.25
    imid
    -0.25
    figure
    -0.25
     Sno
    -0.24
     figure
    -0.24
    ä»ĭåħ¥
    -0.24
    .liferay
    -0.24
    æĿ¥åĪ°äºĨ
    -0.24
    POSITIVE LOGITS
    éĿ¢
    0.27
     theorists
    0.25
    ủ
    0.25
    inals
    0.24
     pundits
    0.24
    aho
    0.24
     Ryder
    0.24
    è¡ĮæĶ¿éĥ¨éŨ
    0.24
    YG
    0.23
    agens
    0.23
    Activations Density 0.004%

    No Known Activations