© 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. 48338
    Prev
    Next
    INDEX
    Explanations

    Rating

    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
    é§
    -0.08
    iffe
    -0.07
     Zob
    -0.07
    erber
    -0.07
    /ws
    -0.07
    çľĭä»ĸ
    -0.07
    सार
    -0.07
     mrb
    -0.07
     magg
    -0.07
    roe
    -0.07
    POSITIVE LOGITS
    åįĥåŃĹ
    0.08
    ÙĨÛĮÙĨ
    0.07
    æĿŀ
    0.07
    atism
    0.07
    fors
    0.07
    à°³
    0.07
    åħ¶ä¸ī
    0.06
    kün
    0.06
    NTAX
    0.06
    åħ¨æĸĩ
    0.06
    Activations Density 0.015%

    No Known Activations