© 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. 35055
    Prev
    Next
    INDEX
    Explanations

    user-related entities and actions

    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
    çĦ¶å¤§
    -0.07
    åħ·åIJĪ
    -0.07
    uzzi
    -0.07
     trasparen
    -0.07
    Ùħاء
    -0.07
    tober
    -0.07
    å²ģéĤ£å¹´
    -0.07
    åįĹè¡Ĺ
    -0.07
    idez
    -0.07
    ä¸įè¡°
    -0.07
    POSITIVE LOGITS
    hood
    0.14
    freund
    0.09
    quake
    0.09
    вига
    0.08
    osemite
    0.08
     Datagram
    0.08
    anova
    0.08
    -facing
    0.08
    ize
    0.08
    cide
    0.08
    Activations Density 0.101%

    No Known Activations