© 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. 4484
    Prev
    Next
    INDEX
    Explanations

    list items

    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
    غ
    -0.08
    ÏģιÏĥ
    -0.07
    intos
    -0.07
    使ä¹ĭ
    -0.07
    Ùħ
    -0.07
    Ø«
    -0.07
    اÙĨ
    -0.07
    áll
    -0.06
    æĸĻçļĦ
    -0.06
    ست
    -0.06
    POSITIVE LOGITS
    ï¸ı
    0.19
    ï¸İ
    0.13
    åĦ¿çļĦ
    0.10
    <|box_end|>
    0.09
    ä½Ĩä¸įéĻIJäºİ
    0.09
    åĦ¿
    0.09
    ¦
    0.08
     à¹Ĩ
    0.08
    à¹Ĩ
    0.07
    ————————————————
    0.07
    Activations Density 0.015%

    No Known Activations