© 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. 18773
    Prev
    Next
    INDEX
    Explanations

    end or permanent state

    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
    è´µåľ¨
    -0.07
    hints
    -0.07
    ä¹ĭåĬŁ
    -0.07
    åºĶå±Ĭ
    -0.07
     interp
    -0.07
     artis
    -0.07
    ä¸ĬåįĬ
    -0.07
    InnerText
    -0.06
    евиÑĩ
    -0.06
    unicode
    -0.06
    POSITIVE LOGITS
     sink
    0.08
    sink
    0.08
     forever
    0.08
    оÑĢÑĤа
    0.08
     permanently
    0.08
    ä¸ĢæŦ
    0.08
    ä¸įåĨįæľī
    0.08
     reachable
    0.08
     Sink
    0.08
    ç»ĵå±Ģ
    0.08
    Activations Density 0.003%

    No Known Activations