© 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. 47432
    Prev
    Next
    INDEX
    Explanations

    (function calls or code blocks)

    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
    upan
    -0.08
    asje
    -0.08
    æīĭéĩĮçļĦ
    -0.07
    wic
    -0.07
    ASON
    -0.07
    +len
    -0.07
     Cali
    -0.07
    ILED
    -0.07
    ãģĵãģĿ
    -0.07
    罪çļĦ
    -0.07
    POSITIVE LOGITS
    erry
    0.07
    onz
    0.07
    änd
    0.06
    '(
    0.06
    angers
    0.06
    eteor
    0.06
    ặn
    0.06
    byt
    0.06
    ť
    0.06
    onne
    0.06
    Activations Density 0.018%

    No Known Activations