© 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. 43701
    Prev
    Next
    INDEX
    Explanations

    detection of technical goods

    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
    åŁİ乡建设
    -0.08
    rame
    -0.07
    rans
    -0.07
    个éĹ®é¢ĺ
    -0.07
    oret
    -0.07
     еÑİ
    -0.07
    croft
    -0.07
     ($(
    -0.07
     ervoor
    -0.07
    <|box_end|>
    -0.07
    POSITIVE LOGITS
     whose
    0.09
     based
    0.07
     cuyos
    0.06
     without
    0.06
    çļĦ人äºĨ
    0.06
     only
    0.06
    主è¦ģåľ¨
    0.06
    æĹ¶ä¹Ł
    0.06
    elier
    0.06
     that
    0.06
    Activations Density 0.449%

    No Known Activations