© 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. 23569
    Prev
    Next
    INDEX
    Explanations

    diagonal front/wise

    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
    inach
    -0.07
    mach
    -0.07
    alak
    -0.07
     soli
    -0.07
    祥
    -0.07
    wick
    -0.07
    sealed
    -0.07
    áĥĵ
    -0.07
    antz
    -0.07
    大å¸Ĥåľº
    -0.07
    POSITIVE LOGITS
    ossip
    0.07
    çĭ¸
    0.07
    anium
    0.07
    é§Ĩãģij
    0.07
    ä¸Ĭåīį
    0.07
    鸳鸯
    0.07
    éĤ»
    0.07
    è²ī
    0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.06
    hattan
    0.06
    Activations Density 0.002%

    No Known Activations