© 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. 16948
    Prev
    Next
    INDEX
    Explanations

    pen input

    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
    ³
    -0.07
    æµ®çĶŁ
    -0.07
    åıĪä¸Ģ个
    -0.06
    .strict
    -0.06
    èĹķ
    -0.06
    æĬ¼
    -0.06
    èļ¤
    -0.06
    engang
    -0.06
    ТÐĴ
    -0.06
    opp
    -0.06
    POSITIVE LOGITS
    带æĿ¥çļĦ
    0.08
     VERSION
    0.08
    -enabled
    0.08
    ewe
    0.07
    æŀģå¤§åľ°
    0.07
    hren
    0.07
    -treated
    0.07
    çĥ¨
    0.07
    ÑģÑĤÑı
    0.07
    ijen
    0.07
    Activations Density 0.054%

    No Known Activations