© 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. 41571
    Prev
    Next
    INDEX
    Explanations

    php code

    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
    ikon
    -0.07
    ogg
    -0.07
    æħİ
    -0.07
    ãģķãģĽãģ¦ãģĦãģŁãģł
    -0.06
    æĪijçŁ¥éģĵäºĨ
    -0.06
    å°½éĩı
    -0.06
    交æĪĺ
    -0.06
     spect
    -0.06
    ç²¾çģµ
    -0.06
    rez
    -0.06
    POSITIVE LOGITS
    满å¿ĥ
    0.08
    çĭł
    0.08
    ç®ķ
    0.07
    çļĨåı¯
    0.07
    èį£åħī
    0.07
    ovas
    0.07
    सà¥įता
    0.07
    ayos
    0.07
    vend
    0.06
    (AT
    0.06
    Activations Density 0.067%

    No Known Activations