© 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. 8299
    Prev
    Next
    INDEX
    Explanations

    gaga

    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
    ehmen
    -0.07
    вÑĥ
    -0.07
     bounced
    -0.07
    teres
    -0.07
    ajo
    -0.06
    phas
    -0.06
    empio
    -0.06
    arus
    -0.06
    åı«æĪij
    -0.06
    িয়
    -0.06
    POSITIVE LOGITS
    soever
    0.08
    æ®ĭ
    0.07
    ä¸Ģåľ°
    0.07
     Gên
    0.07
    ä¸įä½ı
    0.07
    å¤ļå¾Ĺ
    0.07
    ä½ķçŃī
    0.07
    èĦļæīĭ
    0.06
     unserialize
    0.06
     Ouver
    0.06
    Activations Density 0.055%

    No Known Activations