© 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. 768
    Prev
    Next
    INDEX
    Explanations

    resume

    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
    lical
    -0.08
    chenk
    -0.08
    åıĪæľīä»Ģä¹Ī
    -0.08
    ÑħÑĸ
    -0.08
    à¸Ńà¹Ģร
    -0.08
    边走
    -0.07
    izzano
    -0.07
    ortable
    -0.07
    èĨĿ
    -0.07
    缸åħ³èµĦ讯
    -0.07
    POSITIVE LOGITS
    ÙĤÙģ
    0.06
    tere
    0.06
    adecimal
    0.06
    anza
    0.06
     emph
    0.06
    ure
    0.06
    URE
    0.06
    Serial
    0.06
    tb
    0.05
    urd
    0.05
    Activations Density 0.001%

    No Known Activations