© 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. 42585
    Prev
    Next
    INDEX
    Explanations

    a, A, Insert, carefully, review

    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
    æħĪ祥
    -0.07
     piet
    -0.06
    ä¸Ĭ楼
    -0.06
    liess
    -0.06
    gers
    -0.06
    严äºİ
    -0.06
    æľ¬èī²
    -0.06
     ute
    -0.06
    aug
    -0.06
    Ùģار
    -0.06
    POSITIVE LOGITS
    ä¸įåħ¥
    0.08
    åĶī
    0.07
    scratch
    0.07
     rán
    0.07
     Vend
    0.07
    kep
    0.07
    iose
    0.07
     tslib
    0.07
    ä¸Ģ个æĺ¯
    0.07
     elaborado
    0.07
    Activations Density 0.003%

    No Known Activations