© 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. 4847
    Prev
    Next
    INDEX
    Explanations

    Check % or item description

    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
    æĻĴ
    -0.06
    åĢ¼çļĦ
    -0.06
    ogn
    -0.06
    éģµå¾ª
    -0.06
    çİ©æĦıåĦ¿
    -0.06
     staples
    -0.06
     revered
    -0.06
    PathVariable
    -0.06
    åĪ©äºļ
    -0.06
    æįį
    -0.06
    POSITIVE LOGITS
    æĿ¡æĿ¡
    0.08
    ç«ĭãģ¦
    0.08
    è°ħ
    0.08
    λλα
    0.08
    Caller
    0.07
    åħ³å¿ĥçļĦéĹ®é¢ĺ
    0.07
    ืà¸Ńà¸Ļ
    0.07
    çªľ
    0.07
    æľīçļĦåľ¨
    0.07
    Descriptions
    0.07
    Activations Density 0.009%

    No Known Activations