© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32902
    Prev
    Next
    INDEX
    Explanations

    patent of invention

    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
    usercontent
    -0.07
    istik
    -0.07
    atically
    -0.07
    imizer
    -0.07
    jamin
    -0.07
    ogados
    -0.07
    stüt
    -0.07
    ستا
    -0.07
    å±ij
    -0.07
    rored
    -0.07
    POSITIVE LOGITS
    è·¯åĮĹ
    0.08
    lé
    0.07
    代表çĿĢ
    0.07
    óc
    0.06
     Polly
    0.06
    ió
    0.06
    rát
    0.06
    åŁł
    0.06
    entric
    0.06
    æĥ³çĿĢ
    0.06
    Activations Density 1.281%

    No Known Activations