© 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. 63778
    Prev
    Next
    INDEX
    Explanations

    names of people or titles

    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
    ĥģ
    -0.09
    =https
    -0.08
    çİĭæ°¸
    -0.08
    htag
    -0.08
    afia
    -0.08
    ç¿°
    -0.07
    æĸĩ广
    -0.07
    achen
    -0.07
    ë¹Ī
    -0.07
    .baidu
    -0.07
    POSITIVE LOGITS
    é¢ĺå¹²
    0.07
     Cirque
    0.07
    _builtin
    0.07
     ought
    0.07
    Ms
    0.06
    éĻĪè¿°
    0.06
    å¾Ĺåĩºç»ĵ论
    0.06
     Ms
    0.06
     ¬
    0.06
     cause
    0.06
    Activations Density 0.020%

    No Known Activations