© 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. 22-TRANSCODER-HP
    7. 129750
    Prev
    Next
    INDEX
    Explanations

    body

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amus
    -0.29
     unregister
    -0.26
    .shtml
    -0.25
    ãģ¾ãģ¾
    -0.25
    ynchronize
    -0.25
    Pragma
    -0.25
    olicit
    -0.25
    é¢ĸ
    -0.25
     timestep
    -0.25
    fffffff
    -0.24
    POSITIVE LOGITS
    奶
    0.27
    ucer
    0.27
    echo
    0.27
    ç»Ļä½łä»¬
    0.26
    piece
    0.26
     piece
    0.26
     Nature
    0.25
    mail
    0.25
     bare
    0.24
     lact
    0.24
    Activations Density 0.002%

    No Known Activations