© 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. 129512
    Prev
    Next
    INDEX
    Explanations

    report

    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
    âĺ°
    -0.27
    —if
    -0.24
    acci
    -0.23
     GU
    -0.23
    ...");↵
    -0.23
    *time
    -0.23
    åijľ
    -0.22
    æ½¢
    -0.22
    ªĮ
    -0.22
     Passed
    -0.22
    POSITIVE LOGITS
     stoi
    0.28
    èģŀãģı
    0.27
     tand
    0.26
    åĽŀæĿ¥äºĨ
    0.26
    ringe
    0.25
    unte
    0.24
    à¸Ľà¸£à¸²à¸ģà¸ı
    0.23
     undertaking
    0.23
    ç²¾ç¥ŀ
    0.23
    .readValue
    0.22
    Activations Density 0.008%

    No Known Activations