© 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. 19-TRANSCODER-HP
    7. 9137
    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
    ices
    -0.28
    ãĥ¼ãĤº
    -0.28
    ups
    -0.27
    unes
    -0.27
    Td
    -0.26
    iced
    -0.26
    ç²Ĺ
    -0.25
    isches
    -0.25
    ice
    -0.25
     responder
    -0.25
    POSITIVE LOGITS
    =cut
    0.31
    天çĶŁ
    0.30
    InstanceState
    0.29
    -ending
    0.27
    *Math
    0.26
    =val
    0.26
    çļĦè§Ĵèī²
    0.26
    cone
    0.26
     nightclub
    0.25
     hete
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.