© 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. 21049
    Prev
    Next
    INDEX
    Explanations

    franchise series

    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
    mons
    -0.07
    èĪ
    -0.06
    ä¸ĢéĿ¢
    -0.06
    بÙĦ
    -0.06
    èĬ¯
    -0.06
    Singleton
    -0.06
    å¸Ĥ
    -0.06
    ë²Ķ
    -0.06
    ArrayOf
    -0.06
    cal
    -0.06
    POSITIVE LOGITS
    ç³»åĪĹ
    0.12
     series
    0.11
    ç³»åĪĹçļĦ
    0.09
    ãĤ·ãĥªãĥ¼ãĤº
    0.09
    ç³»åĪĹ产åĵģ
    0.09
     séries
    0.09
    çŃīç³»åĪĹ
    0.09
     trilogy
    0.09
    series
    0.09
    -series
    0.08
    Activations Density 0.185%

    No Known Activations