© 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. 28019
    Prev
    Next
    INDEX
    Explanations

    startswith `//` or `+`

    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
    è®®
    -0.06
    顺
    -0.06
    ret
    -0.06
    æĬĸ
    -0.06
    ä¼IJ
    -0.06
    .googlecode
    -0.06
    HA
    -0.06
    以å¤ĸçļĦ
    -0.06
    uye
    -0.06
    æ¯Ķè¾ĥ
    -0.06
    POSITIVE LOGITS
    eza
    0.10
    ä¸įä½ıäºĨ
    0.08
    æľįåĬ¡åįıè®®
    0.08
    èĨĢ
    0.08
     Zwischen
    0.08
    ä¸Ńå¿ĥçŃī
    0.08
    ggio
    0.08
    èĬ¯
    0.08
    icona
    0.08
    xie
    0.08
    Activations Density 0.103%

    No Known Activations