© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11972
    Prev
    Next
    INDEX
    Explanations

    earlier, estimates

    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
    istik
    -0.07
     comunque
    -0.07
    zett
    -0.07
     flexibil
    -0.07
    AsString
    -0.07
    ä¹Łåıªèĥ½
    -0.06
     finalmente
    -0.06
    zó
    -0.06
    ãģ¨ãĤĤ
    -0.06
    ä½ĨæľĢç»Ī
    -0.06
    POSITIVE LOGITS
    åĵªæĢķ
    0.08
    blia
    0.07
    èĢĮä¸Ķè¿ĺæĺ¯
    0.07
     пÑĢиÑĩем
    0.07
    andest
    0.07
    åĵªæĢķæĺ¯
    0.07
    åIJĮæŶè¿ĺè¦ģ
    0.07
    åIJĮæŶè¿ĺ
    0.06
    ç²ī
    0.06
    è§ģåºķ
    0.06
    Activations Density 0.161%

    No Known Activations