© 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. 34845
    Prev
    Next
    INDEX
    Explanations

    figure references

    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
    æĥĬéĻ©
    -0.08
    Marshal
    -0.08
    äºĮåįģäºĮ
    -0.08
    rotch
    -0.07
    orme
    -0.07
    ÅĦczy
    -0.07
    arme
    -0.07
    orma
    -0.07
    äºĮåįģåħŃ
    -0.07
    جÙĪÙĨ
    -0.07
    POSITIVE LOGITS
    å·¥æĪ¿
    0.07
     graz
    0.07
    lp
    0.07
    icide
    0.06
    inite
    0.06
    EP
    0.06
     ÑĤÑĢо
    0.06
    inom
    0.06
    ä¸Ńé«ĺ
    0.06
    olver
    0.06
    Activations Density 0.005%

    No Known Activations