© 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. 58531
    Prev
    Next
    INDEX
    Explanations

    proposal and application submissions

    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
    ettle
    -0.07
    æľĢæĸ°è¯Ħ论
    -0.07
    _export
    -0.07
    åĩºéŨ
    -0.07
    æ¯ķä¸ļçļĦ
    -0.07
    åľŃ
    -0.07
    é¢ģå¸ĥ
    -0.07
     manuten
    -0.07
    导
    -0.06
     uscita
    -0.06
    POSITIVE LOGITS
     submitted
    0.12
     submissions
    0.12
     submission
    0.12
     submitting
    0.11
     submit
    0.11
    ç«ŀäºī
    0.10
    ç«ŀäºīæ¿ĢçĥĪ
    0.10
     competition
    0.10
    submit
    0.10
    submission
    0.10
    Activations Density 0.276%

    No Known Activations