© 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. 46821
    Prev
    Next
    INDEX
    Explanations

    would result

    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
    åį³åı¯æŁ¥çľĭ
    -0.09
    ãģĵãģĨãģĹãģŁ
    -0.08
    åºĶå°½
    -0.08
    è¿Ļåıªæĺ¯
    -0.07
    à¸ģลà¸ĩ
    -0.07
    è¿ĻæŃ£æĺ¯
    -0.07
    å®ĥæīĢ
    -0.07
     иное
    -0.07
    andr
    -0.07
    ulp
    -0.07
    POSITIVE LOGITS
    oret
    0.08
    åĬłæĭ¿å¤§
    0.07
    cludes
    0.07
    å§Ķ书记
    0.07
     includes
    0.07
     leds
    0.07
    æĸ°åĬłåĿ¡
    0.07
    romatic
    0.06
    ally
    0.06
     means
    0.06
    Activations Density 0.018%

    No Known Activations