© 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. 59960
    Prev
    Next
    INDEX
    Explanations

    extract text content

    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
    以对
    -0.07
    ä¼ĺ
    -0.07
    etsk
    -0.07
    ictured
    -0.07
    æĸ°æŃĮ
    -0.07
    é²²
    -0.07
    amentals
    -0.07
    èµĦæĸĻæĺ¾ç¤º
    -0.07
    çĶ±åĽ½å®¶
    -0.07
    æĶ¿æ²»ä»»åĬ¡
    -0.07
    POSITIVE LOGITS
    umah
    0.07
    (include
    0.07
     inclus
    0.07
    ymm
    0.06
    hpp
    0.06
    ()(
    0.06
    æ°
    0.06
    èĨĺ
    0.06
    éĩľ
    0.06
    avid
    0.06
    Activations Density 0.001%

    No Known Activations