© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12089
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols in equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     débit
    -0.07
     ÏĥÏįν
    -0.07
     tuá»ķi
    -0.06
     Perp
    -0.06
    èģĮä¸ļçļĦ
    -0.06
    룡
    -0.06
     Brook
    -0.06
    ibri
    -0.06
    æĽ²æ±Ł
    -0.06
    åıĭ们
    -0.06
    POSITIVE LOGITS
    aye
    0.08
    {$
    0.08
    ç»´çĶŁç´łåĴĮ
    0.07
    antie
    0.07
    ãĢįãĢĮ
    0.07
    yo
    0.07
    ä¸įæ¯Ķ
    0.07
    å¨ģä¿¡
    0.07
    æij
    0.07
    èī
    0.07
    Activations Density 0.016%

    No Known Activations