© 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. 59889
    Prev
    Next
    INDEX
    Explanations

    discovery

    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
    ænd
    -0.06
    istar
    -0.06
    bras
    -0.06
    æĪijæĦ¿æĦı
    -0.06
    aar
    -0.06
    ''.
    -0.06
    æľī人
    -0.06
    orb
    -0.06
    ce
    -0.06
    åħ¨éĥ¨åĨħ容
    -0.06
    POSITIVE LOGITS
    è¿Ļ两ç§į
    0.10
    ãģ©ãģ¡ãĤīãĤĤ
    0.09
     alike
    0.09
    ãģĦãģļãĤĮ
    0.09
    è¿Ļ两款
    0.08
    æľ¬è´¨ä¸Ĭ
    0.08
    ãģ¨ãĤĤãģ«
    0.08
    éĢĻåħ©
    0.08
    éĥ½å±ŀäºİ
    0.08
     beide
    0.08
    Activations Density 0.062%

    No Known Activations