© 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. 34637
    Prev
    Next
    INDEX
    Explanations

    explaining why

    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
    Orig
    -0.07
    åı¯èĥ½ä¼ļ导èĩ´
    -0.07
    оÑĤе
    -0.07
    çľĭèµ·æĿ¥å¾Ī
    -0.06
    æĶ¹åıĺèĩªå·±
    -0.06
    iqu
    -0.06
    çľĭåľ¨çľ¼éĩĮ
    -0.06
    agnar
    -0.06
     Brom
    -0.06
    çľĭèµ·æĿ¥
    -0.06
    POSITIVE LOGITS
    çļĦç¼ĺæķħ
    0.10
    åıĹåĪ°äºĨ
    0.09
     ê·¸ë§Įíģ¼
    0.09
    没æľīæī¾åĪ°
    0.09
    没èĥ½
    0.08
    گار
    0.08
    corso
    0.08
    ä¸ĩä½Ļåħĥ
    0.08
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    0.08
    walker
    0.08
    Activations Density 0.303%

    No Known Activations