© 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. 12-TRANSCODER-HP
    7. 23551
    Prev
    Next
    INDEX
    Explanations

    Rounding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Locator
    -0.25
     repos
    -0.25
    京
    -0.24
    åģľè½¦ä½į
    -0.24
    ä»ĵåĤ¨
    -0.24
    ä¸į幸
    -0.24
    äch
    -0.24
    enda
    -0.24
    udd
    -0.24
    ä»ĵåºĵ
    -0.24
    POSITIVE LOGITS
     ngược
    0.29
    hower
    0.28
    inine
    0.28
     minority
    0.27
    缸åıį
    0.27
    åħĪè¿ĽæĬĢæľ¯
    0.26
    èİĴ
    0.26
     suck
    0.26
    è®´
    0.26
     XCT
    0.25
    Activations Density 0.001%

    No Known Activations