© 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. 23537
    Prev
    Next
    INDEX
    Explanations

    Cos, BOT, Copyright, spacial content

    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
    认å®ļçļĦ
    -0.07
    æĻ¤
    -0.06
    तर
    -0.06
    era
    -0.06
    åįĹ宫
    -0.06
    éĹºå¥³
    -0.06
    ê´Ģ
    -0.06
    oris
    -0.06
    ç¥ĸå®Ĺ
    -0.06
     nonetheless
    -0.06
    POSITIVE LOGITS
    moth
    0.09
    веÑĢи
    0.08
    á»ħu
    0.08
    vertise
    0.08
    imizer
    0.08
     Lump
    0.07
    esco
    0.07
    .invalid
    0.07
    便åĪ©åºĹ
    0.07
    Lazy
    0.07
    Activations Density 0.002%

    No Known Activations