© 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. 41580
    Prev
    Next
    INDEX
    Explanations

    perforators, professors, death, conditions, specific

    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
     تÙĨظÛĮÙħ
    -0.06
    å¼Ģå§ĭåĩºçİ°
    -0.06
    itik
    -0.06
    abu
    -0.06
    æĪijä¸įç¦ģ
    -0.06
    arda
    -0.06
    asia
    -0.06
    æĬķæ¡£
    -0.06
    æ³ķè¯Ń
    -0.06
    ãĤ°ãĥŃãĥ¼
    -0.06
    POSITIVE LOGITS
    åı¯çĶ¨äºİ
    0.16
     suitable
    0.15
    éĢĤåIJĪ
    0.14
    åı¯ä¾Ľ
    0.13
     eligible
    0.13
    åħ·å¤ĩäºĨ
    0.13
    æľĢéĢĤåIJĪ
    0.13
    åı¯ä»¥çĶ¨äºİ
    0.13
    æĽ´éĢĤåIJĪ
    0.13
    éĿŀ常éĢĤåIJĪ
    0.12
    Activations Density 0.311%

    No Known Activations