© 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. 64617
    Prev
    Next
    INDEX
    Explanations

    collect terms in an expression

    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
    IOS
    -0.07
    è¿Ŀåıįä¸Ĭè¿°
    -0.07
    _each
    -0.07
    nock
    -0.07
    anos
    -0.07
    VED
    -0.07
    éķ¿ç©º
    -0.06
     Vod
    -0.06
    èµĺ
    -0.06
    (((
    -0.06
    POSITIVE LOGITS
    ä¸ĥ年级
    0.09
    åħ«å¹´çº§
    0.09
    ä¸ŃèĢĥ
    0.08
    ä¹Ŀ年级
    0.08
    人æķĻçīĪ
    0.08
    åIJĮæ¡Į
    0.08
    çĽ¸ä¿¡ä½ł
    0.08
    墨水
    0.07
    åIJĪä½ľäº¤æµģ
    0.07
    udeau
    0.07
    Activations Density 0.003%

    No Known Activations