© 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. 141696
    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
    ENU
    -0.29
    LastError
    -0.25
    åģ¶
    -0.25
    ILER
    -0.25
     TW
    -0.25
     Father
    -0.24
    çİĦ
    -0.24
     resc
    -0.24
    éĵ²
    -0.24
     fidelity
    -0.23
    POSITIVE LOGITS
    æģ½
    0.32
    $$$
    0.30
    ä¸Ģ段æŶéĹ´
    0.27
     shoot
    0.26
     Airways
    0.25
    ãĥ¡ãĥĩãĤ£ãĤ¢
    0.25
     Whilst
    0.25
    å¼Ģæľº
    0.24
    deo
    0.24
    peat
    0.24
    Activations Density 11.090%

    No Known Activations

    This feature has no known activations.