© 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. 55116
    Prev
    Next
    INDEX
    Explanations

    Iowa

    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
    eln
    -0.08
    .intValue
    -0.08
    egni
    -0.08
    itore
    -0.08
    usch
    -0.08
     Sez
    -0.08
    undi
    -0.08
    /AFP
    -0.07
     boh
    -0.07
    磶
    -0.07
    POSITIVE LOGITS
    åı¬
    0.06
    мени
    0.06
    èģĮ
    0.06
     Funk
    0.06
     Ng
    0.06
     ê±°
    0.06
    æĪĸå¤ļ个
    0.06
    éŃĶç¥ŀ
    0.06
    åѦæ¡Ī
    0.06
    æ´Ľæĸ¯
    0.05
    Activations Density 1.183%

    No Known Activations