© 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. 1317
    Prev
    Next
    INDEX
    Explanations

    meeting, placement, business, comprehensive ownership, tariffs

    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
    çļĦæľīåħ³
    -0.08
    åľ¨éĩĮéĿ¢
    -0.08
     sometime
    -0.08
    使ä¹ĭ
    -0.07
     benutzt
    -0.07
    ä¸įæĺ¯å¾Ī
    -0.07
     somewhat
    -0.07
    yahoo
    -0.07
    æľīå¾Ī
    -0.07
    ç¬ijåĤ²
    -0.07
    POSITIVE LOGITS
    âĢ
    0.09
    æĺ¾èijĹæıIJåįĩ
    0.08
    0.08
    Âł
    0.08
    âĢĮ
    0.07
    å°ĨæĮģç»Ń
    0.07
    âľħ
    0.07
    æĪij们å§ĭç»Ī
    0.07
     [...]
    0.07
    0.07
    Activations Density 0.114%

    No Known Activations