© 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. 49464
    Prev
    Next
    INDEX
    Explanations

    input and output

    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
    èĢĮæĺĵ
    -0.08
    pekt
    -0.08
    manos
    -0.08
    unen
    -0.07
    家åĸ»
    -0.07
    gon
    -0.07
    åIJijè®°èĢħ
    -0.07
    allah
    -0.07
    åģļ强
    -0.07
    ä¸įèĥ½å®Įåħ¨
    -0.07
    POSITIVE LOGITS
    çĤŃ
    0.08
     outputs
    0.07
    æĮīè¦ģæ±Ĥ
    0.07
     emerg
    0.07
     Formatting
    0.06
     output
    0.06
    دة
    0.06
    /console
    0.06
     Tav
    0.06
    $output
    0.06
    Activations Density 0.004%

    No Known Activations