© 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. 24-TRANSCODER-HP
    7. 149546
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izzes
    -0.25
    hall
    -0.25
    lay
    -0.24
    çķ¢ç«Ł
    -0.24
    é»ĺå¥ij
    -0.24
    -archive
    -0.24
    readOnly
    -0.23
    çĺ¦
    -0.23
    åĬŀ好
    -0.23
    uptools
    -0.23
    POSITIVE LOGITS
    omb
    0.27
    夷
    0.26
    象
    0.25
    elist
    0.25
     aup
    0.24
    带
    0.24
    edb
    0.24
    åĽ¾æ¡Ī
    0.23
    ;text
    0.23
    åı¸
    0.23
    Activations Density 1.333%

    No Known Activations

    This feature has no known activations.