© 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. 97610
    Prev
    Next
    INDEX
    Explanations

    0

    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
    .opens
    -0.28
    agner
    -0.28
    äºĮåįģå¹´
    -0.27
    hoa
    -0.26
     UNU
    -0.25
    ultipart
    -0.25
    çĥĤ
    -0.24
    kees
    -0.24
    ETERS
    -0.24
    æĦı大
    -0.24
    POSITIVE LOGITS
     History
    0.28
    åĽŀæĿ¥
    0.28
    unts
    0.27
    ร
    0.26
     recent
    0.25
    History
    0.24
    ä¹IJ趣
    0.24
    rowth
    0.23
    è¿ĩåİ»
    0.23
    uitive
    0.23
    Activations Density 0.033%

    No Known Activations