© 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. 22578
    Prev
    Next
    INDEX
    Explanations

    laser eye surgery and "Q"

    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
    ìĥĺ
    -0.29
     okhttp
    -0.26
    (ofSize
    -0.24
    asking
    -0.24
    encoding
    -0.23
    _resolve
    -0.23
    earable
    -0.23
     æŁ¥è¯¢
    -0.23
    ç¼ĸçłģ
    -0.23
     Await
    -0.23
    POSITIVE LOGITS
    itioner
    0.31
    éªħ
    0.27
     exc
    0.27
    iture
    0.27
    éĺ²
    0.26
     Dem
    0.25
    mix
    0.25
    æ··
    0.25
    itra
    0.25
    inde
    0.25
    Activations Density 0.002%

    No Known Activations