© 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. 9-TRANSCODER-HP
    7. 29409
    Prev
    Next
    INDEX
    Explanations

    ch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦæľīæķĪ
    -0.27
    ĵåIJį
    -0.27
    fir
    -0.26
    layan
    -0.26
     fir
    -0.25
    Chunk
    -0.25
    çļĦè´¨éĩı
    -0.25
    xba
    -0.25
    èĬŁ
    -0.24
    Chunks
    -0.24
    POSITIVE LOGITS
    -General
    0.29
     $($
    0.26
     Campbell
    0.26
     NAN
    0.25
    -mounted
    0.25
     mounting
    0.25
    ilot
    0.24
    -mount
    0.24
    arov
    0.24
     Discipline
    0.24
    Activations Density 0.905%

    No Known Activations