© 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. 8383
    Prev
    Next
    INDEX
    Explanations

    induction, crop, seek, consuming

    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
    å·¥ä½ľå®¤
    -0.08
    _WORDS
    -0.08
    antum
    -0.08
    ÏĨή
    -0.08
    çļĻ
    -0.07
    éĥ½å¾Ī好
    -0.07
    訴
    -0.07
    odate
    -0.07
    æĺ¯äººçĶŁ
    -0.07
    ulls
    -0.07
    POSITIVE LOGITS
    åĢįçļĦ
    0.08
    urement
    0.07
    个åŃIJ
    0.07
    åĢį
    0.06
    æŶåĪĨ
    0.06
    agul
    0.06
    个头
    0.06
    å½Ĵ
    0.06
    使çĶ¨è¯¥
    0.06
    Justin
    0.06
    Activations Density 0.002%

    No Known Activations