© 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. 26127
    Prev
    Next
    INDEX
    Explanations

    explains 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
    _EXIST
    -0.07
    å¦Ĥä½ķè¿Ľè¡Į
    -0.07
    inery
    -0.07
    pector
    -0.07
     Ways
    -0.07
    彬
    -0.07
    ipated
    -0.07
    ectores
    -0.07
    æľīåħ³æĥħåĨµ
    -0.07
    zerw
    -0.07
    POSITIVE LOGITS
    ä¸ĢæĿ¥
    0.12
    åİŁåĽłåľ¨äºİ
    0.10
    ãģĭãĤīãģ§ãģĻ
    0.10
    çļĦç¼ĺæķħ
    0.09
    æĺ¯åĽłä¸º
    0.09
    лÑĮкÑĥ
    0.09
    çļĦåİŁåĽł
    0.09
    because
    0.09
     because
    0.09
    å·¥ä½ľéľĢè¦ģ
    0.09
    Activations Density 0.050%

    No Known Activations