© 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. 35058
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    áĥĵáĥĶ
    -0.08
    Logic
    -0.07
     verr
    -0.07
    èĥ½å¤ŁæľīæķĪ
    -0.07
    è¿IJæ°Ķ
    -0.07
     real
    -0.07
     DISCLAIMER
    -0.06
     overd
    -0.06
    Logs
    -0.06
    Outputs
    -0.06
    POSITIVE LOGITS
     noun
    0.09
    åIJįè¯į
    0.08
     naming
    0.08
     infix
    0.08
     nouns
    0.08
    éľĢè¦ģåľ¨
    0.08
    形容è¯į
    0.08
     suffix
    0.07
    åľ°åIJį
    0.07
    _suffix
    0.07
    Activations Density 0.005%

    No Known Activations