© 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. 24459
    Prev
    Next
    INDEX
    Explanations

    Code/technical writing

    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
     dia
    -0.29
    å¢ŀåĢ¼æľįåĬ¡
    -0.28
    æī§æĶ¿
    -0.26
    æī§æķĻ
    -0.26
     membership
    -0.26
    åĩºåĬ¨
    -0.26
    æī£
    -0.25
    è¦Ĩ
    -0.25
     Hue
    -0.25
    åijĪ
    -0.25
    POSITIVE LOGITS
    unta
    0.28
    asion
    0.26
    izzer
    0.25
    AMES
    0.25
     completes
    0.25
    \Resource
    0.24
    ummies
    0.24
    ино
    0.24
    $template
    0.24
    骸
    0.24
    Activations Density 0.003%

    No Known Activations