© 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. 55322
    Prev
    Next
    INDEX
    Explanations

    introductions describing states

    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
    æķħèĢĮ
    -0.07
    datum
    -0.06
     str
    -0.06
    èĢĮä¸İ
    -0.06
     subsequently
    -0.06
    jenigen
    -0.06
    åĽłèĢĮ
    -0.06
     &,
    -0.06
    èĢĮåħ¶
    -0.06
    appings
    -0.06
    POSITIVE LOGITS
    huri
    0.09
    %!
    0.09
     пожалÑĥй
    0.08
     caranya
    0.08
    è¿Ļä¸įæĺ¯
    0.08
     навеÑĢное
    0.07
    à¹ģห
    0.07
    è¿Ļæĺ¯ä»Ģä¹Ī
    0.07
    èµ·æĿ¥äºĨ
    0.07
    åĩºæĿ¥äºĨ
    0.07
    Activations Density 0.198%

    No Known Activations