© 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. 108389
    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
    AZE
    -0.25
     myself
    -0.25
    apers
    -0.24
    bage
    -0.24
    statements
    -0.24
    身å¿ĥ
    -0.24
    åĽ¢éķ¿
    -0.24
    atus
    -0.23
     Colum
    -0.23
    èĩªæĪij
    -0.23
    POSITIVE LOGITS
     trib
    0.28
    criptive
    0.25
    éĩĮ
    0.24
    -worker
    0.24
    neau
    0.24
     indent
    0.23
     attempted
    0.23
    åĪ¤
    0.23
     obs
    0.23
    åĽłä¸ºå¥¹
    0.23
    Activations Density 1.103%

    No Known Activations

    This feature has no known activations.