© 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. 39790
    Prev
    Next
    INDEX
    Explanations

    frequency and document

    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
    кл
    -0.08
    annis
    -0.08
    alon
    -0.07
    зал
    -0.07
     Tone
    -0.07
    мп
    -0.07
     ó
    -0.07
    èĤĥ
    -0.06
    佬
    -0.06
    ä¹ħä¹ħ
    -0.06
    POSITIVE LOGITS
    åİŁæĿ¥çļĦ
    0.08
    åİŁæľīçļĦ
    0.08
     preservation
    0.08
     Preservation
    0.08
    æĶ¹æİī
    0.07
    åİŁæĿ¥
    0.07
    åİŁæľī
    0.07
     renamed
    0.07
    åIJĮæł·çļĦ
    0.07
    è°ĥæķ´å¥½
    0.07
    Activations Density 0.021%

    No Known Activations