© 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. 17276
    Prev
    Next
    INDEX
    Explanations

    URLs and technical identifiers

    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
    _WRAPPER
    -0.08
    bacher
    -0.08
    _lazy
    -0.07
    ẹn
    -0.07
    ë¥ĺ
    -0.07
    ream
    -0.07
    æµģ
    -0.07
    putc
    -0.07
    weise
    -0.07
    θε
    -0.07
    POSITIVE LOGITS
    echt
    0.08
    rik
    0.07
    æĹ¥åĩºçĶŁ
    0.06
    ontra
    0.06
    è¿Ļä¹Īç®Ģåįķ
    0.06
    _inf
    0.06
    人åijĺ对
    0.06
    ä½łä¸Ģå®ļè¦ģ
    0.06
    åĸľæĢĴåĵĢä¹IJ
    0.06
    et
    0.06
    Activations Density 0.002%

    No Known Activations