© 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. 149742
    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
    é¢Ĩ导èĢħ
    -0.26
    çķĻä¸ĭæĿ¥
    -0.26
    /graphql
    -0.25
    åĩºæīĭ
    -0.25
    itel
    -0.25
     *__
    -0.24
    egis
    -0.24
    arging
    -0.24
    bos
    -0.24
    TEX
    -0.24
    POSITIVE LOGITS
    .system
    0.24
     fizz
    0.23
    anta
    0.23
     PA
    0.23
     scratched
    0.23
     imposs
    0.23
     impossible
    0.22
    å½¢çĬ¶
    0.22
    举
    0.22
    ä¸įå¤ļ
    0.22
    Activations Density 0.951%

    No Known Activations

    This feature has no known activations.