© 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. 1329
    Prev
    Next
    INDEX
    Explanations

    CO, O, Se, $

    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
    es
    -0.07
    ken
    -0.06
    æĸ§
    -0.06
    æ¶
    -0.06
    ish
    -0.06
    æ·¼
    -0.06
     hum
    -0.06
    åħ¨éĥ¨
    -0.05
    æĭİ
    -0.05
    unk
    -0.05
    POSITIVE LOGITS
     sostanzi
    0.08
     dicip
    0.08
     Turnbull
    0.08
    顾åIJįæĢĿ
    0.08
    QualifiedName
    0.08
    ä¸Ĭè¿°ä½ľåĵģ
    0.08
    веÑīение
    0.08
    è¡į
    0.08
    ваÑİÑīее
    0.07
    éĺ³æĺ¥
    0.07
    Activations Density 0.013%

    No Known Activations