© 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. 14994
    Prev
    Next
    INDEX
    Explanations

    list items preceding numbers

    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
    .getSimpleName
    -0.07
    磨çģŃ
    -0.07
    Ń
    -0.07
    ©
    -0.07
    adem
    -0.07
    大éĥ¨åĪĨéĥ½æĺ¯
    -0.07
    åŁºæľ¬çļĦ
    -0.06
    åįģå¤ļå¹´
    -0.06
    åı¦ä¸ĢåįĬ
    -0.06
    istics
    -0.06
    POSITIVE LOGITS
    第
    0.10
     somewhere
    0.09
    ç¼ĸåı·
    0.09
    第åħŃ
    0.08
    åľ¨ç¬¬
    0.08
    年第
    0.08
    çļĦ第
    0.08
    som
    0.08
    :nth
    0.08
    æķĻäºİ
    0.08
    Activations Density 0.008%

    No Known Activations