© 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. 59978
    Prev
    Next
    INDEX
    Explanations

    size discussion volunteer

    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
    rawer
    -0.10
    æĹ¢ä¸į
    -0.08
    egin
    -0.08
    eggi
    -0.08
    idth
    -0.08
    é¢Ĩè·ij
    -0.08
    vény
    -0.08
    iec
    -0.08
    iseur
    -0.08
    rée
    -0.08
    POSITIVE LOGITS
    edly
    0.06
    çļĦ解éĩĬ
    0.06
    ri
    0.06
    ầm
    0.05
    adox
    0.05
    zo
    0.05
    ro
    0.05
    rok
    0.05
    avin
    0.05
    æīī
    0.05
    Activations Density 0.008%

    No Known Activations