© 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. 27015
    Prev
    Next
    INDEX
    Explanations

    variable assignment in code

    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
    htable
    -0.07
    isoft
    -0.07
    ä¿Ŀå®Ī
    -0.07
    apu
    -0.07
    ruit
    -0.07
    åĺĹ
    -0.07
    izzi
    -0.07
    ikian
    -0.07
    inah
    -0.07
    带走äºĨ
    -0.07
    POSITIVE LOGITS
    å¤§æľ¬
    0.08
    atorie
    0.07
    ToDate
    0.06
    zo
    0.06
     nata
    0.06
    ope
    0.06
    DV
    0.06
    emens
    0.06
    æľīåħ³æ³ķå¾ĭæ³ķè§Ħ
    0.06
     tô
    0.06
    Activations Density 0.023%

    No Known Activations