© 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. 13603
    Prev
    Next
    INDEX
    Explanations

    detection limit

    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
    elis
    -0.09
    éľĢè¦ģåIJĮ
    -0.08
    elts
    -0.08
    apg
    -0.08
    ä½İ調
    -0.08
     ëĭ¤ëħĢ
    -0.08
    æIJº
    -0.08
    пÑĢÑı
    -0.07
    _boost
    -0.07
    axter
    -0.07
    POSITIVE LOGITS
     granularity
    0.10
    精度
    0.08
     smallest
    0.07
     digit
    0.07
     finest
    0.07
     minimum
    0.07
    oser
    0.07
    ä¸Ģæ¡£
    0.07
     precision
    0.07
    çĹ
    0.07
    Activations Density 0.018%

    No Known Activations