© 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. 63856
    Prev
    Next
    INDEX
    Explanations

    mathematical and code structure

    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®Įä¹ĭåIJİ
    -0.07
    ains
    -0.07
    uslim
    -0.07
    ä¸Ģä¸įå°ıå¿ĥ
    -0.07
    ä¹ĭä¸Ģå°±æĺ¯
    -0.07
    áĢ½
    -0.07
    åħļå§Ķ书记
    -0.06
    Ïģαι
    -0.06
    -era
    -0.06
    ãģ£ãģ±
    -0.06
    POSITIVE LOGITS
     ìĤ¬ìĿ´ìĹIJ
    0.08
    erville
    0.07
    ritt
    0.07
    ¹Ħ
    0.06
     Sears
    0.06
    åĨįåĪ°
    0.06
    colas
    0.06
    ÏĦίαÏĤ
    0.06
    untime
    0.06
    .blogspot
    0.06
    Activations Density 0.012%

    No Known Activations