© 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. 63899
    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
    figure
    -0.28
    åłij
    -0.27
    åı£å¤´
    -0.26
    åĽ¾
    -0.26
     haircut
    -0.26
    **
    -0.25
    _figure
    -0.25
    ãģ§ãģĻãģĹ
    -0.25
    æĶ¶
    -0.24
    å¼ºåĽ½
    -0.24
    POSITIVE LOGITS
    fony
    0.31
    ä¹ħä¹ħ
    0.27
     söz
    0.26
    riz
    0.25
    ä»Ģä¹Īåij¢
    0.25
    .getError
    0.24
    gist
    0.24
    RH
    0.24
    NSE
    0.24
    Ã¶ÄŁ
    0.24
    Activations Density 8.498%

    No Known Activations

    This feature has no known activations.