© 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. 98240
    Prev
    Next
    INDEX
    Explanations

    Code, URLs, programming

    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
    pins
    -0.26
    OperationException
    -0.25
    ippers
    -0.25
    -centered
    -0.24
    æľ¬èº«
    -0.24
    tring
    -0.24
    èµ·ä¼ı
    -0.24
    iant
    -0.23
    iji
    -0.23
    POSITIVE LOGITS
    è¿Ļ两个
    0.35
    è¿Ļ两
    0.30
    è¿Ļ两ç§į
    0.30
    åı¦ä¸Ģ个
    0.29
    }s
    0.26
    第äºĮ个
    0.26
    æľ¬æĬ¥
    0.26
    -second
    0.25
    åı¦å¤ĸä¸Ģ个
    0.25
     second
    0.25
    Activations Density 0.057%

    No Known Activations