© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 31697
    Prev
    Next
    INDEX
    Explanations

    code snippet delimiters

    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
    dol
    -0.08
    ýv
    -0.07
    uger
    -0.07
    óf
    -0.07
    çłĶ究室
    -0.07
    ami
    -0.07
    Ãłm
    -0.07
    pil
    -0.06
     prezi
    -0.06
    ä¸İæĪij们èģĶç³»
    -0.06
    POSITIVE LOGITS
    ä¸ĩ家
    0.07
    [opt
    0.07
    IRST
    0.07
    ä¸įåİ»
    0.07
    "class
    0.07
    engel
    0.07
    åĬłæĭ¿å¤§
    0.07
     SÆ¡
    0.07
    enom
    0.07
    [Math
    0.06
    Activations Density 0.056%

    No Known Activations