© 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. 18-TRANSCODER-HP
    7. 89182
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¡Įä¸ļä¸Ń
    -0.26
     Princeton
    -0.25
     hate
    -0.24
     waving
    -0.24
     ey
    -0.24
     sourced
    -0.23
    ey
    -0.23
     Sour
    -0.23
    people
    -0.23
     predicates
    -0.23
    POSITIVE LOGITS
    pite
    0.28
    icot
    0.27
    å¼Ń
    0.26
     noqa
    0.26
    æľīè¶³å¤ŁçļĦ
    0.26
     confidently
    0.25
    issa
    0.25
     "[%
    0.25
    [](
    0.25
    upa
    0.24
    Activations Density 0.176%

    No Known Activations

    This feature has no known activations.