© 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. 129918
    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
    ç¥Ī
    -0.26
    _QUAL
    -0.25
    èĶ½
    -0.25
     contributor
    -0.25
    -comm
    -0.24
    é¦IJ
    -0.23
    linger
    -0.23
     orientation
    -0.23
    áºĵ
    -0.23
     Pays
    -0.23
    POSITIVE LOGITS
    imony
    0.30
    ä¸īæĺ¯
    0.30
    LError
    0.28
    \Annotation
    0.27
    зав
    0.25
    çļĦ缸åħ³
    0.25
    çĸij
    0.25
    å¾Ģ
    0.25
    WXYZ
    0.24
    aker
    0.24
    Activations Density 21.475%

    No Known Activations

    This feature has no known activations.