© 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. 20-TRANSCODER-HP
    7. 129492
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Meg
    -0.25
     costly
    -0.23
    ointed
    -0.23
    æĭľ
    -0.23
     indirect
    -0.23
    uchar
    -0.23
    ****************************************************************************
    -0.23
     uninitialized
    -0.22
    ä¿Ŀ驾
    -0.22
    mah
    -0.22
    POSITIVE LOGITS
    idents
    0.30
    ائÙĤ
    0.28
    ä½Ĩ她
    0.27
    çªĪ
    0.27
    flen
    0.27
     Pee
    0.27
    翦
    0.26
     Professionals
    0.26
     paranoid
    0.26
    amo
    0.25
    Activations Density 75.933%

    No Known Activations

    This feature has no known activations.