© 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. 32-TRANSCODER-HP
    7. 41698
    Prev
    Next
    INDEX
    Explanations

    say "months"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åįģä¸ī
    -0.35
    åįģ大
    -0.33
    åįģäºĮ
    -0.32
    åįģä¸īæĿ¡
    -0.31
    apsed
    -0.31
    äºĶå¹´
    -0.31
     nine
    -0.30
    ä¹Ŀ大
    -0.30
     Nine
    -0.29
    年第
    -0.29
    POSITIVE LOGITS
    aticon
    0.27
    ÑĢÑĥÑĪ
    0.25
    licing
    0.24
    人工
    0.23
    utsch
    0.23
    ucher
    0.23
     Fried
    0.23
    RU
    0.23
    mon
    0.23
     nhân
    0.23
    Activations Density 0.004%

    No Known Activations