© 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. 63072
    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
    [args
    -0.27
    忽çĦ¶
    -0.26
     mass
    -0.26
     computational
    -0.25
    dden
    -0.24
    sist
    -0.24
    иÑĢованиÑı
    -0.24
    ç°ª
    -0.23
    ä»İ严
    -0.23
    æ°¢èĥ½
    -0.23
    POSITIVE LOGITS
     zakÅĤad
    0.26
    asto
    0.25
    ular
    0.24
    PAIR
    0.24
     bon
    0.24
     owe
    0.24
    å¦Ĥæŀľçݩ家
    0.23
    emics
    0.23
    ç²¾ç¥ŀçĹħ
    0.23
     Tories
    0.23
    Activations Density 61.304%

    No Known Activations

    This feature has no known activations.