© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32422
    Prev
    Next
    INDEX
    Explanations

    blog URLs and dates

    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
    ’
    -0.07
    以ä¸Ĭ
    -0.07
     non
    -0.07
    以ä¸ĬçļĦ
    -0.06
     “
    -0.06
     rep
    -0.06
    ”
    -0.06
    -
    -0.06
    sek
    -0.06
    /
    -0.06
    POSITIVE LOGITS
    寵
    0.08
    åĬªåĬĽæīĵéĢł
    0.08
    æĢĿæĥ³åĴĮè¡ĮåĬ¨
    0.08
    noÅĽci
    0.08
    ánh
    0.08
    ÙİاÙĨ
    0.08
    æķ¬è¯·åħ³æ³¨
    0.08
    дона
    0.08
    è¿ĶåĽŀ缮å½ķ
    0.08
    INET
    0.08
    Activations Density 0.216%

    No Known Activations