© 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. 41757
    Prev
    Next
    INDEX
    Explanations

    method or class definitions

    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
    ×ķ×Ļ
    -0.07
    ìĶ¬
    -0.07
     Stam
    -0.06
    ände
    -0.06
    ==>
    -0.06
    allest
    -0.06
    mouseleave
    -0.06
    leyen
    -0.06
    å¤ĸéĢģ
    -0.06
    nikov
    -0.06
    POSITIVE LOGITS
    EventManager
    0.07
    IANO
    0.07
    é»Ķ
    0.07
    zung
    0.07
    åı¯è¨Ģ
    0.07
    çļĩåŃIJ
    0.07
    ASSES
    0.07
    ÑĤина
    0.07
    ç¼ĸç¨ĭè¯Ńè¨Ģ
    0.07
    ç®Ĺä¸įä¸Ĭ
    0.07
    Activations Density 0.004%

    No Known Activations