© 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. 15708
    Prev
    Next
    INDEX
    Explanations

    Numbers followed by nouns

    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
     Lour
    -0.08
    vol
    -0.08
    inton
    -0.07
    umat
    -0.07
    egar
    -0.07
     multiline
    -0.07
    ilor
    -0.07
    expl
    -0.07
    èµ·è§ģ
    -0.07
     fek
    -0.07
    POSITIVE LOGITS
    fold
    0.08
    æĶ¯æŁ±
    0.08
     cardinal
    0.08
     ê°Ģì§Ģ
    0.07
    junto
    0.07
    teen
    0.07
    边走
    0.07
    æŁ±
    0.07
     kinds
    0.07
    ä¸Ģä½ĵ
    0.07
    Activations Density 0.085%

    No Known Activations