© 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. 130285
    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
     joking
    -0.25
    å¼Ģçİ©ç¬ij
    -0.24
    è°ĥä¾ĥ
    -0.24
    åĩ¼
    -0.24
    _measure
    -0.24
     perce
    -0.24
    迨
    -0.24
    toBeInTheDocument
    -0.24
    InputElement
    -0.23
     (()
    -0.23
    POSITIVE LOGITS
     Baker
    0.26
     Prop
    0.26
    ä¸Ģå®ļ
    0.26
    pp
    0.26
    ató
    0.25
    suit
    0.25
     Lower
    0.24
    hol
    0.24
    è¯Ŀ
    0.24
    [#
    0.24
    Activations Density 63.215%

    No Known Activations

    This feature has no known activations.