© 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. 3028
    Prev
    Next
    INDEX
    Explanations

    not possible, error, crashing

    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
    ÙİدÙĴ
    -0.08
    pson
    -0.08
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    -0.07
    ellone
    -0.07
    以ä¸ĭåĩłçĤ¹
    -0.07
    aré
    -0.07
    以ä¸ĭåĩłä¸ª
    -0.07
    éĺħè¯»æľ¬æĸĩ
    -0.07
    usco
    -0.07
    νÏİ
    -0.07
    POSITIVE LOGITS
    æĽ´ä½ķåĨµ
    0.08
    éĻ¤éĿŀ
    0.08
     unless
    0.07
    åĪ«è¯´
    0.07
    å²ij
    0.06
    åıªè¦ģ
    0.06
    ä½ķåĨµ
    0.06
    unless
    0.06
    eger
    0.06
    alf
    0.06
    Activations Density 0.006%

    No Known Activations