© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 98890
    Prev
    Next
    INDEX
    Explanations

    period

    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
    ute
    -0.28
    encia
    -0.26
    ä¸įå°ij
    -0.26
     accru
    -0.25
    ula
    -0.25
    recover
    -0.24
    è´´
    -0.24
    iable
    -0.24
    uate
    -0.24
    éĵ¾
    -0.24
    POSITIVE LOGITS
    è¿Ļ两ç§į
    0.28
    nym
    0.27
     //=
    0.27
    åĩłç§į
    0.26
    ä¼¼ä¹İæĺ¯
    0.26
    cac
    0.25
    hurst
    0.25
    NFL
    0.24
     VÅ©
    0.24
    vvm
    0.24
    Activations Density 0.003%

    No Known Activations