© 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. 4612
    Prev
    Next
    INDEX
    Explanations

    what is meant by

    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
    rasil
    -0.09
    åħĭæĸ¯åĿ¦
    -0.08
    ´Ī
    -0.08
     susc
    -0.08
    égi
    -0.08
    undler
    -0.08
    culares
    -0.08
    presi
    -0.08
    /umd
    -0.08
    å¥Ķ
    -0.08
    POSITIVE LOGITS
    åIJ«ä¹ī
    0.16
     meaning
    0.15
     meanings
    0.14
    çļĦåIJ«ä¹ī
    0.14
    æĦıåij³çĿĢ
    0.12
    ä»Ģä¹ĪæĦıæĢĿ
    0.12
    æĦıæĢĿ
    0.12
    主è¦ģæĺ¯æĮĩ
    0.12
    æĦıæĢĿæĺ¯
    0.12
    æĦıæĮĩ
    0.12
    Activations Density 0.071%

    No Known Activations