© 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. 55202
    Prev
    Next
    INDEX
    Explanations

    speaking to others

    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
     inter
    -0.07
    ãģĬ
    -0.06
     Rien
    -0.06
    çĶ¨ä¸Ĭ
    -0.06
     fict
    -0.06
    ledon
    -0.06
    åŁºåľ°å»ºè®¾
    -0.06
    oyer
    -0.06
    ä½IJ
    -0.05
     гÑĢамоÑĤ
    -0.05
    POSITIVE LOGITS
    åIJİç»ŃçļĦ
    0.11
    åIJİç»Ń
    0.11
    åIJİéĿ¢çļĦ
    0.10
     subsequent
    0.10
    åľ¨åħ¶ä»ĸ
    0.10
     thereafter
    0.10
     subsequently
    0.10
    çļĦåħ¶ä»ĸ
    0.09
     forthcoming
    0.09
     elsewhere
    0.09
    Activations Density 0.673%

    No Known Activations