© 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. 63640
    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
    ometown
    -0.27
    åľ¨å½ĵåľ°
    -0.26
    cam
    -0.25
    åįĥä¸ĩ
    -0.25
    lington
    -0.24
     Redistributions
    -0.24
    иÑĤеÑĤ
    -0.24
     sinon
    -0.24
    èŀįåIJĪ
    -0.24
    åħ¨åĮº
    -0.24
    POSITIVE LOGITS
    setLayout
    0.29
    ém
    0.28
    <v
    0.27
    çºłéĶĻ
    0.26
     Gro
    0.26
    <a
    0.25
    иÑĩ
    0.25
    <u
    0.25
    丫
    0.24
    oha
    0.24
    Activations Density 32.800%

    No Known Activations

    This feature has no known activations.