© 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. 22780
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    washer
    -0.26
     sixth
    -0.25
    åĽŀåİ»
    -0.24
    赤
    -0.24
     TestUtils
    -0.24
     Tango
    -0.24
     fifth
    -0.24
    ä¸ĵä¸ļæĬĢæľ¯
    -0.23
    æ°ijéĹ´
    -0.23
    åĢĻéĢī
    -0.23
    POSITIVE LOGITS
    为客æĪ·
    0.29
    ä½ĵéªĮ
    0.29
    ä¸ŃåŃĺåľ¨çļĦ
    0.27
    é«Ķé©Ĺ
    0.26
    <*
    0.25
     yönet
    0.24
    acman
    0.24
    endment
    0.24
    管çIJĨåĪ¶åº¦
    0.24
     Yönet
    0.24
    Activations Density 0.001%

    No Known Activations