© 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. 65426
    Prev
    Next
    INDEX
    Explanations

    calculus and expectation

    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
     utr
    -0.08
    ØŃÙģ
    -0.07
    è½
    -0.07
    raga
    -0.07
    avo
    -0.07
    lando
    -0.07
    kah
    -0.06
    _constructor
    -0.06
    rag
    -0.06
    rese
    -0.06
    POSITIVE LOGITS
    haber
    0.09
    kke
    0.07
    å¼ķ
    0.07
    å¼ķè¿Ľ
    0.07
    ä¸Ģæīĭ
    0.06
    Beer
    0.06
    warten
    0.06
     municip
    0.06
    åѤç«ĭ
    0.06
    bish
    0.06
    Activations Density 0.006%

    No Known Activations