© 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. 46038
    Prev
    Next
    INDEX
    Explanations

    numbers and parameters

    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
    çļĦä¸Ģ个éĩįè¦ģ
    -0.08
    çļĦè¿Ļä¸Ģ
    -0.07
    çļĦä¸Ģ项éĩįè¦ģ
    -0.07
    éĥ¨ç»ıçIJĨ
    -0.07
    á»ĥn
    -0.07
    æľī个
    -0.07
    åī¯çIJĨäºĭéķ¿
    -0.07
    çļĦéĤ£ä¸ª
    -0.07
    ä¸ĢèģĮ
    -0.07
    .arch
    -0.06
    POSITIVE LOGITS
    åĪĨåĪ«ä¸º
    0.11
     respectively
    0.11
    åĪĨåĪ«æĺ¯
    0.10
     values
    0.10
    å®ĥ们æĺ¯
    0.10
     these
    0.09
    è¿ĻäºĽä¸ľè¥¿
    0.09
    these
    0.09
     These
    0.09
    åĪĨåĪ¥
    0.08
    Activations Density 0.125%

    No Known Activations