© 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. 45277
    Prev
    Next
    INDEX
    Explanations

    associated documentation

    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
     volna
    -0.11
    stens
    -0.09
    aver
    -0.09
    वà¥Ģ
    -0.08
    istry
    -0.08
    Ùħاء
    -0.08
    اسب
    -0.08
    ening
    -0.08
    ymar
    -0.08
    gestellt
    -0.08
    POSITIVE LOGITS
    -sama
    0.09
    ä¸įæĺİçļĦ
    0.07
    imuth
    0.07
    اتÙĩÙħ
    0.07
    ounter
    0.07
    èµ·æĿ¥
    0.07
    arana
    0.07
    ively
    0.07
     nhau
    0.06
    ieg
    0.06
    Activations Density 0.069%

    No Known Activations