© 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. 30-TRANSCODER-HP
    7. 96220
    Prev
    Next
    INDEX
    Explanations

    Time units

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åİŁåĪĻ
    -0.24
    è½½
    -0.24
     searched
    -0.24
    åŁºæľ¬åİŁåĪĻ
    -0.24
    å¹³
    -0.23
     Alb
    -0.23
    endent
    -0.23
    enger
    -0.23
    onor
    -0.23
    Advertisement
    -0.22
    POSITIVE LOGITS
    ä¸Ģå¹´
    0.70
    ä¸Ģ天
    0.68
    ä¸Ģå¹´å¤ļ
    0.59
    两年
    0.59
    ä¸īå¹´
    0.58
    ä¸ī天
    0.58
    ä¸Ģ个æľĪ
    0.57
     year
    0.57
     months
    0.56
     weeks
    0.55
    Activations Density 0.925%

    No Known Activations