© 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. 129830
    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
    arkin
    -0.27
    _stand
    -0.25
    izont
    -0.24
    .clf
    -0.24
    straight
    -0.23
    '],['
    -0.23
    .Hand
    -0.23
     straight
    -0.23
    麽
    -0.23
    æ¦Ķ
    -0.23
    POSITIVE LOGITS
    quiv
    0.26
    éĻ¢
    0.26
    éķ¿å¤§
    0.25
    stead
    0.25
     Agenda
    0.24
    ç½ijçĤ¹
    0.24
    åĩī
    0.24
    åĩłå¼ł
    0.24
    jen
    0.23
    äºĨåįĬ天
    0.23
    Activations Density 12.427%

    No Known Activations

    This feature has no known activations.