© 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. 8972
    Prev
    Next
    INDEX
    Explanations

    folded twice

    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
    kiye
    -0.06
    zano
    -0.06
    orro
    -0.06
     ((__
    -0.06
    .cx
    -0.06
    ulo
    -0.06
     Sang
    -0.06
    ätter
    -0.06
    åŁºç¡Ģ
    -0.06
    ساÙĨ
    -0.06
    POSITIVE LOGITS
     likewise
    0.08
    éĢļåĪĻ
    0.08
    ä¹Łå¸ĮæľĽ
    0.08
     rap
    0.08
    ä½ľåĪĻ
    0.08
    亦çĦ¶
    0.07
    åĪĻæĺ¯
    0.07
    èĭ±æĸĩåIJįåŃĹ
    0.07
    inga
    0.07
     же
    0.07
    Activations Density 0.454%

    No Known Activations