© 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. 4640
    Prev
    Next
    INDEX
    Explanations

    use to inner dont and - facilitate with , you

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ç«ĭ
    -0.07
    åĩij
    -0.07
    awah
    -0.07
    éľ²
    -0.07
     grind
    -0.06
     loc
    -0.06
     cita
    -0.06
    æĺ¾
    -0.06
    çĮĿ
    -0.06
     cit
    -0.06
    POSITIVE LOGITS
    订éĺħä¸ĵæłı
    0.09
    มีà¸ģาร
    0.09
    æĥ³çŁ¥éģĵçļĦçŃĶæ¡Ī
    0.08
    è¯Ŀ说
    0.08
    bury
    0.08
     erfol
    0.07
    ãĥ«ãĥķ
    0.07
     erfolgt
    0.07
    antly
    0.07
    vida
    0.07
    Activations Density 0.352%

    No Known Activations