© 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. 34740
    Prev
    Next
    INDEX
    Explanations

    java input reading

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ihal
    -0.08
    ós
    -0.07
    ensee
    -0.07
    çļĦåij½è¿IJ
    -0.07
    åij½è¿IJ
    -0.07
    estad
    -0.07
    大åıij
    -0.07
    justice
    -0.07
    jev
    -0.07
    ciano
    -0.07
    POSITIVE LOGITS
    ä¸ŃèģĮ
    0.08
    anced
    0.07
    ments
    0.07
    æĮ¨
    0.06
    [in
    0.06
    andle
    0.06
    tere
    0.06
    hu
    0.06
     EAR
    0.06
    ãģ¤ãģ¾ãĤĬ
    0.06
    Activations Density 0.006%

    No Known Activations