© 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. 6976
    Prev
    Next
    INDEX
    Explanations

    start position or condition

    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
    æ°¸åĪ©
    -0.09
    imity
    -0.08
    ampo
    -0.08
    ought
    -0.08
    견
    -0.08
    &o
    -0.08
    对äºİéĤ£äºĽ
    -0.07
    инÑĥ
    -0.07
     sza
    -0.07
    urement
    -0.07
    POSITIVE LOGITS
    äºİ
    0.10
     from
    0.07
     with
    0.07
    ä¸ĢåĽŀ
    0.06
    æĸ¼
    0.06
    çĿĢä¸Ģ
    0.06
    /m
    0.06
    entially
    0.06
    ãģĭãĤī
    0.06
    ä¹ĭåĪĿ
    0.06
    Activations Density 0.046%

    No Known Activations