© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9003
    Prev
    Next
    INDEX
    Explanations

    will not

    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
    ä¹Łæĺ¯è¿Ļæł·
    -0.07
    _ix
    -0.07
    è¿Ļæł·å°±åı¯ä»¥
    -0.07
    ä¸įçĶ¨åĨį
    -0.06
    acket
    -0.06
    ä¹Łåĸľæ¬¢
    -0.06
    åıªè¦ģä½ł
    -0.06
    æľªåıĬæŶ
    -0.06
    _queues
    -0.06
    æĪijçĪ±
    -0.06
    POSITIVE LOGITS
    æĹłä»¥
    0.11
    å¾Ĵ
    0.10
    æĹłä»İ
    0.08
    å°±åıªèĥ½
    0.08
     обойÑĤиÑģÑĮ
    0.08
    å°±æĹłæ³ķ
    0.08
    ä¸įçŁ¥æīĢ
    0.07
    @m
    0.07
     merely
    0.07
    黯çĦ¶
    0.07
    Activations Density 0.104%

    No Known Activations