© 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. 37649
    Prev
    Next
    INDEX
    Explanations

    PhD and dissertation

    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
    ory
    -0.09
    cott
    -0.08
     keyed
    -0.08
    kong
    -0.08
    ilet
    -0.08
    æľ¬çīĪ
    -0.08
    éĢ¢
    -0.07
    顶å±Ĥ
    -0.07
    转载èĩ³
    -0.07
    ì¹Ļ
    -0.07
    POSITIVE LOGITS
    sil
    0.06
     abstract
    0.06
    æ¯ģ
    0.06
     graphs
    0.06
    aison
    0.06
     optar
    0.06
    æĬ¥åĪ°
    0.06
    æ¥Ķ
    0.06
     requirements
    0.06
    åħ«å¹´
    0.06
    Activations Density 0.110%

    No Known Activations