© 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. 24-TRANSCODER-HP
    7. 150577
    Prev
    Next
    INDEX
    Explanations

    do

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ienne
    -0.28
     egret
    -0.27
     vide
    -0.26
    igne
    -0.25
     Saunders
    -0.25
    èıľ
    -0.24
    losed
    -0.24
    伪
    -0.23
    ven
    -0.23
     //.
    -0.23
    POSITIVE LOGITS
    faith
    0.29
     faith
    0.26
    é¢Ħæ¡Ī
    0.24
    arity
    0.24
    yard
    0.24
     deal
    0.24
    emarks
    0.24
    æѧ
    0.24
    resar
    0.24
     external
    0.24
    Activations Density 1.034%

    No Known Activations