© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14313
    Prev
    Next
    INDEX
    Explanations

    in situ generation

    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
    åĵ¡
    -0.09
    edException
    -0.08
    chen
    -0.08
    ÑģÑı
    -0.07
    èĹıåľ¨
    -0.07
    stens
    -0.07
    دÙĩ
    -0.07
    ysi
    -0.07
    naires
    -0.07
    åijĺ
    -0.07
    POSITIVE LOGITS
    /on
    0.11
    /out
    0.11
    ï¸İ
    0.10
    /down
    0.09
    /off
    0.09
    /up
    0.09
     módon
    0.08
    iras
    0.08
    aneously
    0.08
    ently
    0.08
    Activations Density 0.121%

    No Known Activations