© 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. 39980
    Prev
    Next
    INDEX
    Explanations

    matchup right

    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
    _increase
    -0.07
    ähr
    -0.07
    æĻĵæĺİ
    -0.07
    è¿ijå¹³
    -0.07
     <![
    -0.07
    RANDOM
    -0.07
     seeded
    -0.07
    ç´§äºĨ
    -0.07
    ToFit
    -0.07
    Random
    -0.07
    POSITIVE LOGITS
    æķĻåѦèµĦæºIJ
    0.07
    交æį¢
    0.07
    ụp
    0.07
    åıĸ
    0.07
    odont
    0.06
     outright
    0.06
    halle
    0.06
    æİī
    0.06
    ç®Ķ
    0.06
    vendor
    0.06
    Activations Density 0.005%

    No Known Activations