© 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. 39773
    Prev
    Next
    INDEX
    Explanations

    results in

    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
    çĬĢ
    -0.08
    ä¸įåĢ¦
    -0.07
    ä»İ没
    -0.07
    rame
    -0.07
    ä¸įå¿ĺ
    -0.07
    缨
    -0.07
    ä¸įéĻIJ
    -0.07
    注æĦıçļĦæĺ¯
    -0.07
    æľīéģĵ
    -0.07
    -ish
    -0.07
    POSITIVE LOGITS
    ãģĽãģ£ãģĭãģı
    0.13
    æĹłæ³ķæŃ£å¸¸
    0.12
    大æīĵæĬĺæī£
    0.11
    å°±æĹłæ³ķ
    0.10
    ä¹ŁæĹłæ³ķ
    0.10
    失åİ»äºĨ
    0.10
    失åİ»
    0.10
    å¾Ĺä¸įåĪ°
    0.09
    éĶĻ失
    0.09
    丧失äºĨ
    0.09
    Activations Density 0.136%

    No Known Activations