© 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. 19849
    Prev
    Next
    INDEX
    Explanations

    given the following

    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
    éħ
    -0.07
    å½Ŀ
    -0.06
    èĭŁ
    -0.06
    为è°ģ
    -0.06
    ä¸Ŀ
    -0.06
    åħ®
    -0.06
    大æľī
    -0.06
    ä¸ĵ家ä»ĭç»į
    -0.06
    弩
    -0.06
     latent
    -0.06
    POSITIVE LOGITS
    以ä¸Ĭ
    0.09
    iant
    0.08
    以ä¸ĭæĿ¡ä»¶
    0.08
    kesan
    0.08
    bourg
    0.08
    ardash
    0.08
    æŀĹåŃIJ
    0.08
    æŃ¤èµ·å½¼
    0.07
     ABOVE
    0.07
    æľĢæĸ°æĸĩç«ł
    0.07
    Activations Density 0.001%

    No Known Activations