© 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. 26522
    Prev
    Next
    INDEX
    Explanations

    return original value

    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¤ļ线ç¨ĭ
    -0.07
    retta
    -0.07
    åı¯æģ¶
    -0.07
    åħ¼æĢ»ç»ıçIJĨ
    -0.07
    ä¸ĭè½½å®īè£ħ
    -0.07
    enger
    -0.07
    御åı²
    -0.07
    andra
    -0.07
    leigh
    -0.07
    petto
    -0.07
    POSITIVE LOGITS
     formatted
    0.07
     pertinent
    0.07
    å®Įæķ´çļĦ
    0.07
     appropriate
    0.07
     contents
    0.07
    溶
    0.06
    大æĪIJ
    0.06
     details
    0.06
     previously
    0.06
     corrected
    0.06
    Activations Density 0.229%

    No Known Activations