© 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. 27-TRANSCODER-HP
    7. 9739
    Prev
    Next
    INDEX
    Explanations

    Technical documents/research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     even
    -0.31
     legal
    -0.26
    æłĸ
    -0.25
    ced
    -0.25
    çĶļèĩ³
    -0.25
     characters
    -0.24
     maximum
    -0.24
     fid
    -0.24
    umed
    -0.23
    oultry
    -0.23
    POSITIVE LOGITS
    ingham
    0.27
    PT
    0.27
    PCS
    0.26
     Serum
    0.26
    Nothing
    0.25
    andon
    0.25
    åĩĿ
    0.25
    ä¸ĢæŃ¥
    0.25
    çıŃ
    0.25
    idan
    0.25
    Activations Density 0.000%

    No Known Activations