© 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. 34063
    Prev
    Next
    INDEX
    Explanations

    continuation or mission

    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
    å¥Ĺ
    -0.07
    ÃŃnh
    -0.07
    ÙĬص
    -0.07
    èĢ³è¾¹
    -0.07
     sol
    -0.06
    æŶæľī
    -0.06
    ç»ıæµİæįŁå¤±
    -0.06
    ulos
    -0.06
    orean
    -0.06
    αι
    -0.06
    POSITIVE LOGITS
    ationToken
    0.08
    åij³
    0.07
    å¿ħè¦ģ
    0.07
    é¾Ļçıł
    0.07
    ETE
    0.07
     montag
    0.07
    æļĹå¤ľ
    0.07
    ÃģC
    0.07
    /ge
    0.07
    _fixture
    0.07
    Activations Density 0.013%

    No Known Activations