© 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. 6973
    Prev
    Next
    INDEX
    Explanations

    exchange or return

    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
    Negative Logits
    gara
    -0.07
    éĢĤåºĶèĥ½åĬĽ
    -0.07
    说å®Į
    -0.07
    incu
    -0.07
    ئة
    -0.07
    ondern
    -0.07
    ENCIA
    -0.07
    æŀģå¯Į
    -0.07
    ICI
    -0.07
    æĤ²æ¬¢
    -0.07
    POSITIVE LOGITS
    交æį¢
    0.13
     reciprocal
    0.13
     recip
    0.13
     exchange
    0.12
     recipro
    0.12
     вза
    0.12
    æį¢åıĸ
    0.12
    æį¢æĿ¥
    0.11
    exchange
    0.11
     exchanged
    0.11
    Activations Density 0.084%

    No Known Activations