© 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. 41908
    Prev
    Next
    INDEX
    Explanations

    OLYMPIC DISTRICT COURT Register

    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
    új
    -0.06
    лÑĮ
    -0.06
    õt
    -0.06
    Å¡a
    -0.06
    Å¡i
    -0.06
    ÑİÑĢ
    -0.06
    å¦Ĥæŀľèĩªå·±
    -0.06
    ÂŃtion
    -0.06
     Harr
    -0.06
     Dor
    -0.06
    POSITIVE LOGITS
    Tunes
    0.08
    天ä¹ĭ
    0.08
    æ°ıæĹı
    0.07
    <|im_start|>
    0.07
    Stamped
    0.07
    éŃĶåħ½
    0.07
    ANGAN
    0.07
    éķ¶
    0.07
    YRO
    0.07
    ฯ
    0.07
    Activations Density 0.326%

    No Known Activations