© 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. 23-TRANSCODER-HP
    7. 24188
    Prev
    Next
    INDEX
    Explanations

    scientific/medical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¢Ļå£ģ
    -0.33
    æIJħ
    -0.31
    -validator
    -0.27
     contingency
    -0.27
    _wh
    -0.26
     rocks
    -0.26
    çŁ³å¤´
    -0.26
    æĪIJåijĺåįķä½į
    -0.26
    å²©çŁ³
    -0.26
    æĪIJåijĺ
    -0.26
    POSITIVE LOGITS
     gaps
    0.29
     pockets
    0.28
    éļĻ
    0.28
    rent
    0.27
    ocket
    0.27
    open
    0.26
    å¼ĢæĶ¾
    0.26
    ullen
    0.25
    æ´ŀ
    0.25
    eries
    0.25
    Activations Density 0.006%

    No Known Activations