© 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. 88502
    Prev
    Next
    INDEX
    Explanations

    units of time

    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
    tright
    -0.27
    æ¯ıå¹´
    -0.27
    åĿļæĮģ
    -0.26
    ä¸Ŀ
    -0.26
    åĨĮ
    -0.26
    级
    -0.25
    ä¸Ńåįİ
    -0.25
    åħīè¾ī
    -0.25
    åºŁ
    -0.25
     worm
    -0.24
    POSITIVE LOGITS
    ÐIJÐŀ
    0.27
     adul
    0.26
    kus
    0.26
    PIO
    0.25
    aday
    0.24
    襻
    0.24
    itud
    0.23
    .Reporting
    0.23
    bread
    0.23
    AAD
    0.23
    Activations Density 0.013%

    No Known Activations