© 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. 39788
    Prev
    Next
    INDEX
    Explanations

    column names or code structures

    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
    æ¿®
    -0.06
    æ®ĭ
    -0.06
    åħĭç¦ı
    -0.06
    -
    -0.06
    .g
    -0.06
    宽
    -0.06
     probabil
    -0.06
    oud
    -0.06
    /
    -0.06
    ä¸ĩåıª
    -0.06
    POSITIVE LOGITS
     #__
    0.09
    idata
    0.09
    rame
    0.09
    apie
    0.09
    -badge
    0.08
     ÐķÑģÑĤе
    0.08
     onDataChange
    0.08
    æĢ»ç½²
    0.08
    teh
    0.08
    ಡಿ
    0.08
    Activations Density 0.072%

    No Known Activations