© 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. 44275
    Prev
    Next
    INDEX
    Explanations

    early, junior, prior, freshman

    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
    å©ļåIJİ
    -0.08
     adult
    -0.08
    *((
    -0.07
    èĬ³èįī
    -0.07
    æĪIJ人
    -0.07
    irsch
    -0.07
    æľŁå¾ħçļĦ
    -0.07
    মান
    -0.07
    éķ¿å¤§äºĨ
    -0.07
    imba
    -0.07
    POSITIVE LOGITS
    æĽ´æĹ©
    0.18
     earlier
    0.16
     preceding
    0.14
     Earlier
    0.14
    Earlier
    0.13
     beforehand
    0.13
    æĹ©
    0.12
    è¾ĥæĹ©
    0.12
    åľ¨æѤä¹ĭåīį
    0.11
    çļĦåīįæľŁ
    0.11
    Activations Density 0.292%

    No Known Activations