© 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. 19011
    Prev
    Next
    INDEX
    Explanations

    section markers and citations

    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
    au
    -0.08
    ail
    -0.06
    _LOOKUP
    -0.06
    éĴ³
    -0.06
    rap
    -0.06
    acol
    -0.06
     plunged
    -0.06
    ãĥ§
    -0.06
    ,st
    -0.06
     Dol
    -0.06
    POSITIVE LOGITS
    неÑĤа
    0.08
    ık
    0.07
    å¢ĥ
    0.07
    ár
    0.07
    .exports
    0.07
    Õ¸ÖĤÕ¶
    0.07
    ORE
    0.06
    ì¥IJ
    0.06
    "](
    0.06
     (()
    0.06
    Activations Density 0.003%

    No Known Activations