© 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. 64862
    Prev
    Next
    INDEX
    Explanations

    objects and parts

    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
    衣衫
    -0.08
    å¦ĤçĥŁ
    -0.07
    çľ¼å¸ĺ
    -0.07
    å¹¢
    -0.07
    ahoma
    -0.07
    ÙĪجة
    -0.07
    åįłæľī
    -0.07
    èİĵ
    -0.07
    anship
    -0.07
    dir
    -0.06
    POSITIVE LOGITS
    çĶ¨ä½ľ
    0.11
    åħħå½ĵ
    0.10
     unused
    0.10
    æĭ¿æĿ¥
    0.10
    åı¯ä»¥çĶ¨æĿ¥
    0.09
    åı¯ä»¥ä½ľä¸º
    0.09
    æĶ¹éĢł
    0.08
    æĭ¿ä¾Ĩ
    0.08
    åĨįåĪ©çĶ¨
    0.08
    unused
    0.08
    Activations Density 0.193%

    No Known Activations