© 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. 64556
    Prev
    Next
    INDEX
    Explanations

    abnormal NHC complexes

    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
    ihi
    -0.07
    ewan
    -0.07
    æĺ¯æĮīçħ§
    -0.07
     Lagu
    -0.07
     po
    -0.07
    ì§
    -0.06
    çĪĽ
    -0.06
    ĻĤ
    -0.06
    æĺ¯æīĢæľī
    -0.06
    æľīæĥħ
    -0.06
    POSITIVE LOGITS
    arts
    0.09
    ç´¢
    0.08
    rasil
    0.08
    继èĢĮ
    0.08
    ä¸įèĩ³
    0.07
     Torres
    0.07
    accent
    0.07
    usia
    0.07
    achim
    0.07
     Sicilia
    0.07
    Activations Density 0.002%

    No Known Activations