© 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. 4907
    Prev
    Next
    INDEX
    Explanations

    ring name or identifier

    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
    -0.09
    å½ĵåħ¶
    -0.07
    纳æĸ¯
    -0.07
    d
    -0.06
    1
    -0.06
     di
    -0.06
    2
    -0.06
     slo
    -0.06
    3
    -0.06
    5
    -0.05
    POSITIVE LOGITS
    -secret
    0.09
    obil
    0.09
    ounder
    0.09
    ì¡´
    0.08
    -Smith
    0.08
    áf
    0.08
    ibil
    0.08
    ä¼ļåIJİ
    0.08
    åĨ
    0.08
    اÙħÙĨ
    0.08
    Activations Density 0.001%

    No Known Activations