© 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. 34162
    Prev
    Next
    INDEX
    Explanations

    -like descriptions

    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
    łĢ
    -0.08
    umbang
    -0.07
    OrFail
    -0.07
    åıĬåħ¶
    -0.07
    ä¸į管æĺ¯
    -0.07
     _$
    -0.07
    éĤ£ä¹Īå¤ļ
    -0.07
    udiant
    -0.07
    åľ¨æĿŃå·ŀ
    -0.07
    å¥Īä½ķ
    -0.07
    POSITIVE LOGITS
    -like
    0.13
    å¼ıçļĦ
    0.10
    å¼ı设计
    0.08
    -style
    0.08
    èĪ¬çļĦ
    0.07
    ìĭĿìľ¼ë¡ľ
    0.07
     unders
    0.07
    å¼ı
    0.07
    çĬ¶çļĦ
    0.07
    类似çļĦ
    0.07
    Activations Density 0.027%

    No Known Activations