© 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. 33420
    Prev
    Next
    INDEX
    Explanations

    method or attribute access

    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
    smarty
    -0.06
    æĴŀä¸Ĭ
    -0.06
    éĻµåİ¿
    -0.06
    ikel
    -0.06
    çĶ¨åĪĢ
    -0.06
    æĶ¶äºİ
    -0.06
    è¡Ģ液ä¸Ń
    -0.06
    гин
    -0.06
    å®ģåĮº
    -0.06
    wiÄĻ
    -0.06
    POSITIVE LOGITS
    iop
    0.07
    زش
    0.07
    è¿Ļä¸ªä¸ľè¥¿
    0.07
    ä½ķçŃī
    0.07
     annat
    0.07
    arya
    0.07
    erstand
    0.07
    è´¯
    0.07
     spons
    0.07
    åŃ¦ä¹łç¬Ķè®°
    0.07
    Activations Density 0.037%

    No Known Activations