© 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. 44243
    Prev
    Next
    INDEX
    Explanations

    special characters following `čč`

    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
    å¾Ĺä½ı
    -0.07
    aspers
    -0.07
    ä½Ĩè¿Ļ
    -0.07
    sson
    -0.07
    åIJĪçī©
    -0.07
    èĢĮèµ°
    -0.06
    enton
    -0.06
    ivot
    -0.06
    å·²ä¸İ
    -0.06
    riott
    -0.06
    POSITIVE LOGITS
    nip
    0.08
    иÑİ
    0.07
    bruck
    0.07
    çĶ¨å·¥
    0.07
    hausen
    0.07
    лове
    0.07
    icer
    0.07
    äºĶèĬ±
    0.07
    onga
    0.07
    اÙĩ
    0.07
    Activations Density 0.078%

    No Known Activations