© 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. 28433
    Prev
    Next
    INDEX
    Explanations

    #include <iostream>

    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
    dings
    -0.07
    >>
    -0.07
    uhi
    -0.07
    åı£è¢ĭéĩĮ
    -0.06
    >>>
    -0.06
    enti
    -0.06
    ç²Ł
    -0.06
    krim
    -0.06
    afari
    -0.06
    ListNode
    -0.06
    POSITIVE LOGITS
    สัà¸ģ
    0.08
    ayat
    0.07
    éĴ°
    0.07
    asmine
    0.07
    à¸ģุล
    0.07
    istribu
    0.07
    å®ķ
    0.07
    ั
    0.07
     sick
    0.07
    Ðijо
    0.07
    Activations Density 0.004%

    No Known Activations