© 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. 27871
    Prev
    Next
    INDEX
    Explanations

    incorrect or invalid behavior

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.10
    ç»İ
    -0.08
    kort
    -0.08
    anship
    -0.08
     unmist
    -0.08
    wick
    -0.08
    resent
    -0.08
    quires
    -0.08
     uninterrupted
    -0.08
    ×ķת
    -0.07
    POSITIVE LOGITS
    /out
    0.10
    eous
    0.08
    /un
    0.08
    erweise
    0.08
    /dis
    0.08
    ellaneous
    0.08
    æĪĸå°ij
    0.08
    enheim
    0.07
    а
    0.07
    ly
    0.07
    Activations Density 0.058%

    No Known Activations