© 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. 44296
    Prev
    Next
    INDEX
    Explanations

    find or prove function

    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
    äºļè¿IJ
    -0.08
    subj
    -0.08
    èĩªçĶ¨
    -0.08
    imy
    -0.07
    дж
    -0.07
    >[]
    -0.07
    ç½ijåıĭçļĦ
    -0.07
    çļĦåIJĮ
    -0.07
    LLU
    -0.07
    ForResource
    -0.07
    POSITIVE LOGITS
    天ä¸ĭ第ä¸Ģ
    0.08
    rief
    0.06
    çļĦçŃĶæ¡Ī
    0.06
    erez
    0.06
    éķ¿ä¹ħ
    0.06
    çŃĶæ¡Īæĺ¯
    0.06
    worthy
    0.06
    ickle
    0.06
    اص
    0.06
    ichtung
    0.06
    Activations Density 0.005%

    No Known Activations