© 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. 129978
    Prev
    Next
    INDEX
    Explanations

    known

    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
    ç²¾
    -0.32
    laps
    -0.27
    太大
    -0.27
    éķ¿å¤§
    -0.26
    被认为æĺ¯
    -0.25
    sonian
    -0.25
    ç®Ĺæĺ¯
    -0.24
    .broadcast
    -0.24
    çĸij
    -0.23
     hesitate
    -0.23
    POSITIVE LOGITS
    оÑģÑĤи
    0.26
    ...'↵
    0.26
    isé
    0.25
    åºĶæĢ¥ç®¡çIJĨ
    0.25
    ..."↵
    0.25
    èij©
    0.25
    CKER
    0.24
    [
    0.24
     [
    0.24
    _MO
    0.24
    Activations Density 0.018%

    No Known Activations