© 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. 3039
    Prev
    Next
    INDEX
    Explanations

    world-class

    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
    åŃ½
    -0.08
    chap
    -0.07
    اÙħØ©
    -0.07
     Gord
    -0.07
     designated
    -0.07
    广大
    -0.07
     Barker
    -0.07
    istique
    -0.07
    åIJīåĪ©
    -0.07
    arence
    -0.06
    POSITIVE LOGITS
    öra
    0.07
    Thunk
    0.07
    Locator
    0.07
    ằn
    0.07
    overn
    0.07
    çĭ¬åįł
    0.06
    ัà¹īà¸Ļ
    0.06
    marshall
    0.06
    å±ķåı°
    0.06
    roke
    0.06
    Activations Density 0.001%

    No Known Activations