© 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. 10915
    Prev
    Next
    INDEX
    Explanations

    J. Am

    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
    æĺĵåľ°
    -0.08
    odiac
    -0.08
    rolley
    -0.07
    esium
    -0.07
    åıĪ没æľī
    -0.07
    é»ĺé»ĺçļĦ
    -0.07
    iece
    -0.07
    ugh
    -0.07
    ä¸īåĽ½æ¼Ķä¹ī
    -0.07
    gram
    -0.07
    POSITIVE LOGITS
    hurst
    0.08
    çŃ·åŃIJ
    0.07
    æľĿ天
    0.06
    åijĹ
    0.06
    èĩ´
    0.06
    è¤Ĵ
    0.06
    BUR
    0.06
    ಡಿ
    0.06
    ãģĺ
    0.06
    åį¯
    0.06
    Activations Density 0.013%

    No Known Activations