© 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. 32443
    Prev
    Next
    INDEX
    Explanations

    product of

    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
    indow
    -0.09
    atures
    -0.08
    estad
    -0.08
    ibur
    -0.08
    èĥĸåŃIJ
    -0.08
    Ù°
    -0.08
    ลà¹Į
    -0.08
    Úº
    -0.08
    ä½ķåľ°
    -0.08
     directrice
    -0.08
    POSITIVE LOGITS
    eur
    0.10
    ivity
    0.10
    ìħĪ
    0.09
    sWith
    0.09
    uum
    0.08
    IVITY
    0.08
    ially
    0.07
    -produ
    0.07
    ive
    0.07
    iple
    0.07
    Activations Density 0.017%

    No Known Activations