© 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. 130406
    Prev
    Next
    INDEX
    Explanations

    code/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
    anca
    -0.27
    çľĭæĿ¥
    -0.26
     ['.
    -0.26
    @c
    -0.24
    __()↵
    -0.24
     {}".
    -0.23
    arium
    -0.23
     })();↵
    -0.23
    ÐĴидео
    -0.23
     ();↵
    -0.23
    POSITIVE LOGITS
    ãĢģ
    0.40
    ãĢģ“
    0.38
    ､
    0.35
    ä¼ģä¸ļåĴĮ
    0.34
    ãĢģãĢģ
    0.33
    ï¼īãĢģ
    0.32
    ãĢģãĢĮ
    0.31
    ,:,
    0.30
    ãĢįãĢĮ
    0.29
    ?,?,?,?,
    0.29
    Activations Density 0.008%

    No Known Activations