© 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. 1933
    Prev
    Next
    INDEX
    Explanations

    careerregular seasonjournalism

    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
    aleb
    -0.07
    æĪ¶
    -0.06
    angnya
    -0.06
    æĥ³å¾Ĺ
    -0.06
    éĸ£
    -0.06
    æĪ·
    -0.06
    _CONF
    -0.06
    è¨ŃåĤĻ
    -0.06
    设å¤ĩ
    -0.06
    婺
    -0.06
    POSITIVE LOGITS
    å¼Ģå§ĭäºĨ
    0.11
    æŃ£å¼ıå¼Ģå§ĭ
    0.10
    å¼Ģå§ĭ
    0.10
    çİ°åľ¨å¼Ģå§ĭ
    0.10
    å°ĨæĮīçħ§
    0.09
    _BEGIN
    0.09
    æĪijå¼Ģå§ĭ
    0.09
    -begin
    0.08
    å¼Ģå§ĭåIJİ
    0.08
    å¼Ģå§ĭçļĦ
    0.08
    Activations Density 0.198%

    No Known Activations