© 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. 24816
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    uja
    -0.30
    éļ¾æĢª
    -0.27
    uala
    -0.26
     influ
    -0.25
     margins
    -0.25
    éĵº
    -0.25
    asin
    -0.25
     integrity
    -0.25
     cine
    -0.24
     poly
    -0.24
    POSITIVE LOGITS
    eres
    0.28
    Disp
    0.25
    itar
    0.23
    ä¸Ģæľµ
    0.23
    eric
    0.23
    .published
    0.23
    eland
    0.23
    éľ¹
    0.23
     DISP
    0.23
     Disp
    0.23
    Activations Density 0.143%

    No Known Activations

    This feature has no known activations.