© 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. 35-TRANSCODER-HP
    7. 39213
    Prev
    Next
    INDEX
    Explanations

    Code and foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sit
    -0.31
    nof
    -0.27
     eventual
    -0.26
    ç»Ļ她
    -0.26
    ç»Ļ人
    -0.26
     mentioned
    -0.26
    以åIJİ
    -0.25
    ç»Ļä»ĸ们
    -0.25
     intended
    -0.25
    ATER
    -0.25
    POSITIVE LOGITS
    躬
    0.26
     Jennings
    0.25
     IQueryable
    0.25
    étique
    0.25
     Inspiration
    0.25
    iaux
    0.25
    éĩįè¦ģä½ľçĶ¨
    0.24
    ç½®ä¸ļ
    0.24
     columnName
    0.24
    éļħ
    0.23
    Activations Density 0.135%

    No Known Activations