© 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. 51380
    Prev
    Next
    INDEX
    Explanations

    by [noun phrase]

    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
    éĿĴå°ijå¹´çļĦ
    -0.09
    女åŃ©çļĦ
    -0.09
    expertise
    -0.08
    æ¯ıä¸Ģ个人çļĦ
    -0.08
    æ¯ı个人çļĦ
    -0.08
    éĿĴå¹´çļĦ
    -0.08
    å°ijå¹´çļĦ
    -0.08
    女人çļĦ
    -0.08
    å¥ł
    -0.08
    æķĻå¸ĪçļĦ
    -0.08
    POSITIVE LOGITS
     biais
    0.08
     virtue
    0.07
    ç³»ç»Łåľ¨
    0.07
    kilde
    0.07
    åħ¶åIJİ
    0.07
     ordenador
    0.07
    å§ĭèĩ³
    0.06
     successive
    0.06
     soins
    0.06
    /to
    0.06
    Activations Density 0.758%

    No Known Activations