© 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. 95617
    Prev
    Next
    INDEX
    Explanations

    Questions

    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
    èĢĮæĿ¥
    -0.31
    éĿŀ常å¤ļ
    -0.29
    éĢĻä¸Ģ
    -0.27
     immensely
    -0.26
    åĩłä¹İæĺ¯
    -0.26
    å¹¾ä¹İ
    -0.25
     tremendously
    -0.24
     almost
    -0.24
    ç§ijæĬĢ大åѦ
    -0.24
     numeros
    -0.24
    POSITIVE LOGITS
     some
    0.52
    ä¸ĢäºĽ
    0.47
    some
    0.41
    äºĽ
    0.38
     Some
    0.37
    æľīäºĽ
    0.36
    Some
    0.36
     SOME
    0.32
    .some
    0.32
    _some
    0.32
    Activations Density 0.115%

    No Known Activations