© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39956
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mot
    -0.26
    ai
    -0.26
    .
    -0.26
     survives
    -0.26
     records
    -0.26
    white
    -0.26
    le
    -0.25
    èŀºæĹĭ
    -0.25
     applies
    -0.25
     missing
    -0.25
    POSITIVE LOGITS
    RowAt
    0.27
    ä¸įä½ı
    0.26
    ItemAt
    0.26
    AINS
    0.26
    ebin
    0.24
    onomÃŃa
    0.24
    æݨèįIJéĺħ读
    0.23
    [np
    0.23
    iming
    0.23
    åľ°ä¸Ń
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.