© 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. 3237
    Prev
    Next
    INDEX
    Explanations

    Leader and Deputy

    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
     cess
    -0.06
     ±
    -0.06
    åı²å¯Ĩæĸ¯
    -0.06
    æľī计åĪĴ
    -0.06
    ç¨ĭ
    -0.06
    äºĭäºĭ
    -0.06
    æµİ
    -0.06
    ä½łå·²ç»ı
    -0.06
     circ
    -0.06
    å¾·éŁ³
    -0.06
    POSITIVE LOGITS
     KHO
    0.08
    áh
    0.08
    paru
    0.08
     Lá»ĩ
    0.08
    天çĶŁ
    0.08
    å¾·æĸ¯
    0.08
    pend
    0.08
    innie
    0.08
    ανο
    0.08
    ·¸
    0.07
    Activations Density 0.002%

    No Known Activations