© 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. 55164
    Prev
    Next
    INDEX
    Explanations

    critical value definition

    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
    æľĪ以æĿ¥
    -0.08
    adt
    -0.08
    agini
    -0.08
    æĿĢæīĭ
    -0.07
    (^
    -0.07
    åħ´åįİ
    -0.07
    éĥ½å¿«
    -0.07
    gow
    -0.07
    INLINE
    -0.07
    gun
    -0.07
    POSITIVE LOGITS
    emark
    0.07
    ustos
    0.07
    ponce
    0.07
    occo
    0.06
    ogue
    0.06
    临çķĮ
    0.06
    quio
    0.06
    iosi
    0.06
    çĩķ
    0.06
    imoni
    0.06
    Activations Density 0.006%

    No Known Activations