© 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. 25715
    Prev
    Next
    INDEX
    Explanations

    particular integral

    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
    measurement
    -0.08
    tür
    -0.08
    æµĭéĩı
    -0.07
    eldet
    -0.07
    illow
    -0.07
    ndern
    -0.07
    Measurement
    -0.07
     Measurement
    -0.07
    egna
    -0.07
    acular
    -0.07
    POSITIVE LOGITS
    ุล
    0.08
     Mannheim
    0.07
    éĴĪ对æĢ§çļĦ
    0.07
    EFE
    0.07
    étr
    0.07
    è¶ķ
    0.06
    atre
    0.06
    åĵĢ
    0.06
    ä¸įèµ°
    0.06
     Sticky
    0.06
    Activations Density 0.002%

    No Known Activations