© 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. 42291
    Prev
    Next
    INDEX
    Explanations

    sentence breaks

    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
    abcdefgh
    -0.07
    _OID
    -0.07
    eix
    -0.06
     <<-
    -0.06
    à¹Ģหม
    -0.06
    prs
    -0.06
    enz
    -0.06
    ixe
    -0.06
     âĢŀ
    -0.06
    POSITIVE LOGITS
    aner
    0.08
    reau
    0.07
    å¥İ
    0.07
    äºĮä¸ī
    0.07
     vaan
    0.06
    é³Į
    0.06
    é¢ģ
    0.06
    ä¸įè¦ģå¿ĺè®°
    0.06
    éĺ¿å§Ĩæĸ¯
    0.06
    è´¼
    0.06
    Activations Density 0.092%

    No Known Activations