© 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. 45459
    Prev
    Next
    INDEX
    Explanations

    distance between location or current

    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
     ;
    -0.07
    æĬĺä¼ĺæĥł
    -0.07
    ÙģÙĨ
    -0.07
    åıijå±ķæĪIJ为
    -0.06
    ;
    -0.06
     contrast
    -0.06
    ä¸ĢæĹģçļĦ
    -0.06
     comp
    -0.06
    orgen
    -0.06
    åħīæĺ¯
    -0.06
    POSITIVE LOGITS
     ÙĪبÙĬÙĨ
    0.20
     lẫn
    0.09
    ä½łè¿ĺæĺ¯
    0.09
    ãĤĤãģ®ãģ¨
    0.08
     ׾×ij
    0.08
    "})
    0.08
    å®ŀéĻħåĩºåıij
    0.08
    æĪijè¿ĺæĺ¯
    0.08
    ":"","
    0.08
     ê²ĥê³¼
    0.08
    Activations Density 0.508%

    No Known Activations