© 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. 57632
    Prev
    Next
    INDEX
    Explanations

    Ê, å, Â

    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
    ä½łæ°¸è¿ľ
    -0.07
    Ł
    -0.07
    .spotify
    -0.07
    ozn
    -0.07
    è¿Ļç§įä¸ľè¥¿
    -0.07
    వా
    -0.07
    chluss
    -0.07
    æĦŁæĥ³
    -0.07
    ury
    -0.07
    ä»ħä½ľåıĤèĢĥ
    -0.07
    POSITIVE LOGITS
    Âł
    0.09
    ‘
    0.08
     ‘
    0.07
     Âł
    0.07
    åł
    0.06
    EV
    0.06
    å®ķ
    0.06
    phin
    0.06
    anno
    0.06
    udit
    0.06
    Activations Density 0.086%

    No Known Activations