© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44133
    Prev
    Next
    INDEX
    Explanations

    implicit, via, or e.g

    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
    utant
    -0.07
    寡
    -0.07
    /--
    -0.07
    Õ©
    -0.07
    夥
    -0.07
    çŃīçļĦ
    -0.06
    hu
    -0.06
    olest
    -0.06
    æĹłæ¯Ķ
    -0.06
    czÄħ
    -0.06
    POSITIVE LOGITS
    orit
    0.07
    å½Ĵç»ĵ
    0.07
    impl
    0.07
    iet
    0.07
    qü
    0.06
    alt
    0.06
    ç®ĢåĮĸ
    0.06
    Bool
    0.06
    çŃĨ
    0.06
    ãģ¾ãģ¤
    0.06
    Activations Density 0.002%

    No Known Activations