© 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. 52006
    Prev
    Next
    INDEX
    Explanations

    main(String[] args)

    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
    ROL
    -0.07
    ç³
    -0.07
    ä¹İåħ¶
    -0.07
    olk
    -0.07
    intang
    -0.07
     negatively
    -0.07
    ieras
    -0.07
    笹
    -0.07
    zec
    -0.07
    peria
    -0.07
    POSITIVE LOGITS
    ä¸įåĪ°çļĦ
    0.08
    ¤
    0.07
    ItemCount
    0.07
    giv
    0.07
    ä¸į管æĺ¯
    0.07
     radios
    0.06
    ä¸įæ±Ĥ
    0.06
    illis
    0.06
    à¹Ħ
    0.06
    esen
    0.06
    Activations Density 0.005%

    No Known Activations