© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6765
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à´´
    -0.31
    è´¢
    -0.26
    ERIC
    -0.26
    çĭİ
    -0.25
    Eric
    -0.24
    éĻIJãĤĬ
    -0.24
    depends
    -0.24
    #pragma
    -0.24
    éĢIJ
    -0.23
    梨
    -0.23
    POSITIVE LOGITS
    ials
    0.25
    sted
    0.25
     missing
    0.25
     translated
    0.25
    uple
    0.25
     swept
    0.25
    ious
    0.24
    é¢Ĺ
    0.24
    iously
    0.24
     amounts
    0.24
    Activations Density 0.062%

    No Known Activations

    This feature has no known activations.