© 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. 21667
    Prev
    Next
    INDEX
    Explanations

    ok but

    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
    å¿ħæľī
    -0.08
    ç¡®ä¿Ŀå®īåħ¨
    -0.08
    åİĮ
    -0.08
    ject
    -0.08
    æĺ¾èĢĮæĺĵè§ģ
    -0.07
    cina
    -0.07
    astikan
    -0.07
    ÑģÑĤавки
    -0.07
    ocken
    -0.07
    peg
    -0.07
    POSITIVE LOGITS
    _ENCODING
    0.08
    ä¸įåIJĮçļĦæĺ¯
    0.07
     BUT
    0.07
     However
    0.07
    çĦ¶èĢĮ
    0.07
     however
    0.07
    aging
    0.07
    illers
    0.07
    æĬĢæľ¯ä¸Ĭ
    0.07
    However
    0.07
    Activations Density 0.023%

    No Known Activations