© 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. 26995
    Prev
    Next
    INDEX
    Explanations

    about: description: url:

    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
    .tbl
    -0.08
    åĬĽå£«
    -0.08
     steady
    -0.07
    转载请注æĺİåĩºå¤Ħ
    -0.07
    ibaba
    -0.06
    leet
    -0.06
    è¶Ĭæĥ³
    -0.06
    åħ¨æľ¬å°ı说
    -0.06
    ç´¢æĢ§
    -0.06
    aset
    -0.06
    POSITIVE LOGITS
    Ģ
    0.07
    lime
    0.07
    acie
    0.07
    åħ´ä¸ļ
    0.07
    arking
    0.06
    нÑij
    0.06
    pst
    0.06
    ä¸īåħ«
    0.06
    nonnull
    0.06
    æ²ī
    0.06
    Activations Density 0.047%

    No Known Activations