© 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. 63755
    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
    -team
    -0.24
    ãģĿãĤĮãģ§ãĤĤ
    -0.24
     Gio
    -0.24
    -ne
    -0.23
    æĺ¯æľĢ好çļĦ
    -0.23
    ashion
    -0.23
    èµ°åĩº
    -0.23
    èĹı
    -0.23
     onChanged
    -0.23
    SHOT
    -0.23
    POSITIVE LOGITS
    ách
    0.26
    建
    0.25
    ær
    0.25
    át
    0.25
    æī§åĭ¤
    0.24
    edom
    0.24
     bigint
    0.24
    åı¦æľī
    0.23
    .shapes
    0.23
    çĮĽçĦ¶
    0.23
    Activations Density 49.964%

    No Known Activations

    This feature has no known activations.