© 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. 689
    Prev
    Next
    INDEX
    Explanations

    greek letters (sigma, alpha, beta, delta, gamma)

    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
    ly
    -0.11
    nya
    -0.11
    çĦ¶æĺ¯
    -0.09
    s
    -0.09
    liness
    -0.09
    ng
    -0.09
    ÙħاÙĨ
    -0.09
    yr
    -0.08
    scape
    -0.08
    ãĥ£
    -0.08
    POSITIVE LOGITS
    ation
    0.08
    èī²åĪĹ
    0.08
    voud
    0.08
    ization
    0.07
    isht
    0.07
    ington
    0.07
    ëij¥
    0.07
    jects
    0.07
    acce
    0.07
    -beta
    0.07
    Activations Density 0.078%

    No Known Activations