© 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. 58991
    Prev
    Next
    INDEX
    Explanations

    cells and clones

    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
    inato
    -0.08
     EDUCA
    -0.08
    失çģµ
    -0.07
     Himself
    -0.07
    ëm
    -0.07
    åī¯å±Ģéķ¿
    -0.07
     conservatism
    -0.06
    ool
    -0.06
    æĪijä¿©
    -0.06
    flik
    -0.06
    POSITIVE LOGITS
     cells
    0.10
     clones
    0.10
    Clone
    0.09
    cells
    0.09
     cultured
    0.09
    åŁ¹åħ»
    0.09
     clone
    0.09
     cultures
    0.08
    ç»Ĩèĥŀ
    0.08
     transf
    0.08
    Activations Density 0.457%

    No Known Activations