© 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. 44143
    Prev
    Next
    INDEX
    Explanations

    coronary, flat, compact, quasi, stroke, normal

    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
    æ´»äºĨ
    -0.06
    éŁ³æłĩ
    -0.06
    ancellor
    -0.06
    ãĤ¤ãĥĦ
    -0.06
    æİĴ
    -0.06
    oglob
    -0.06
    åĪ«
    -0.06
    uar
    -0.06
    æIJŃ
    -0.06
    коÑĤа
    -0.06
    POSITIVE LOGITS
    Ŀ
    0.09
    ações
    0.08
    Indented
    0.07
    essai
    0.07
    elsey
    0.07
    acoes
    0.07
    nick
    0.07
    à¹Īà¸Ńม
    0.07
    ação
    0.07
    æĺŃ
    0.07
    Activations Density 1.583%

    No Known Activations