© 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. 51984
    Prev
    Next
    INDEX
    Explanations

    primes and punctuation

    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
    à¯ģ
    -0.09
    satz
    -0.09
    aan
    -0.08
    àŃį
    -0.08
    krit
    -0.08
    alak
    -0.08
    IMUM
    -0.08
    ipse
    -0.08
    chetti
    -0.08
    PILE
    -0.07
    POSITIVE LOGITS
    ãĥ£
    0.10
    Ñı
    0.08
    /'
    0.07
    룬
    0.07
    eds
    0.07
    ity
    0.07
    å¨ĺåŃIJ
    0.07
    omis
    0.07
    asant
    0.07
    ÙĬاء
    0.07
    Activations Density 0.040%

    No Known Activations