© 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. 30-TRANSCODER-HP
    7. 95108
    Prev
    Next
    INDEX
    Explanations

    Moon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    resse
    -0.30
    deriv
    -0.28
    jac
    -0.27
    January
    -0.27
     periods
    -0.26
     serialVersionUID
    -0.25
    dess
    -0.25
     serif
    -0.24
     Directions
    -0.24
     jan
    -0.23
    POSITIVE LOGITS
    å¼ĢäºĨ
    0.30
     Hank
    0.29
    è·ijäºĨ
    0.29
    atorio
    0.27
    æĢİä¹Īæł·
    0.26
     programme
    0.26
    ç¨ĭ
    0.25
    ouro
    0.25
    UNCH
    0.25
    á»Ńa
    0.25
    Activations Density 0.106%

    No Known Activations