© 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. 56938
    Prev
    Next
    INDEX
    Explanations

    order, frustration, hardness, modulation, overlap, skew, censor

    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
    ä¸ĩ次
    -0.08
    ردة
    -0.07
    æľįåĬ¡æľīéĻIJåħ¬åı¸
    -0.07
    使çĶ¨æŶ
    -0.07
    _SELF
    -0.07
    mise
    -0.07
    út
    -0.07
    次çļĦ
    -0.07
    ä¸İæĸ¹æ³ķ
    -0.07
    å¼Ģå¿ĥçļĦ
    -0.06
    POSITIVE LOGITS
    ç¨ĭ度
    0.14
    ç¨ĭ度çļĦ
    0.10
    ç¨ĭ度ä¸Ĭ
    0.09
    度
    0.09
    çļĦç¨ĭ度
    0.09
    ç³»æķ°
    0.08
    ä½ĵçİ°åľ¨
    0.08
    åĽłåŃIJ
    0.08
     extent
    0.08
     caused
    0.08
    Activations Density 0.031%

    No Known Activations