© 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. 107868
    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
    anes
    -0.25
    干货
    -0.25
    ampoline
    -0.25
    客æĪ·æıIJä¾Ľ
    -0.24
    iked
    -0.24
    @js
    -0.24
     Biggest
    -0.24
     galer
    -0.24
    apons
    -0.23
     Against
    -0.23
    POSITIVE LOGITS
     reliably
    0.26
    Jam
    0.25
     ham
    0.24
    åħ¸åŀĭ
    0.24
     Ham
    0.24
    æ´½
    0.24
     Jam
    0.23
    uras
    0.23
     collided
    0.23
    åĬ¡å®ŀ
    0.23
    Activations Density 9.719%

    No Known Activations

    This feature has no known activations.