© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 23760
    Prev
    Next
    INDEX
    Explanations

    Code/Web characters

    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
    rim
    -0.28
     ern
    -0.27
    eger
    -0.26
     thing
    -0.25
     imp
    -0.24
     rod
    -0.24
    ugh
    -0.24
     lip
    -0.24
     **
    -0.24
     hindi
    -0.24
    POSITIVE LOGITS
    stad
    0.29
    ponsors
    0.28
    ogenesis
    0.26
    _funcs
    0.26
    ysql
    0.25
    morph
    0.24
    _macros
    0.24
    /slick
    0.24
    ailles
    0.24
    cash
    0.24
    Activations Density 0.005%

    No Known Activations