© 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. 141984
    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
    è¿ĺæĥ³
    -0.31
    PRI
    -0.27
    rik
    -0.26
    rink
    -0.25
    éĢĿ
    -0.25
    ro
    -0.25
     solder
    -0.25
    rost
    -0.25
    lit
    -0.25
    佶
    -0.25
    POSITIVE LOGITS
    osphate
    0.28
    ETO
    0.27
    exo
    0.25
     allem
    0.25
    cycl
    0.25
    æĿ¡è¯Ħ论
    0.25
    RB
    0.24
    .Immutable
    0.24
    ï¼Įé»ĺ认
    0.24
     liberty
    0.23
    Activations Density 2.535%

    No Known Activations

    This feature has no known activations.