© 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. 142281
    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
    ä¸īå±Ĥ
    -0.25
    æݧåĪ¶åĻ¨
    -0.25
     Fi
    -0.25
    .Formatter
    -0.24
     Fellow
    -0.24
     turnovers
    -0.24
     reco
    -0.24
    osc
    -0.24
     mole
    -0.24
     uns
    -0.24
    POSITIVE LOGITS
    Mot
    0.27
    (sol
    0.26
    buch
    0.25
    /trunk
    0.25
    èĸ¤
    0.24
    igy
    0.24
    ihad
    0.24
    .jpa
    0.24
     sol
    0.24
    alance
    0.24
    Activations Density 71.394%

    No Known Activations

    This feature has no known activations.