© 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. 51913
    Prev
    Next
    INDEX
    Explanations

    merely followed by a verb or noun phrase

    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
    abis
    -0.09
    ç´¢æĢ§
    -0.09
    缴åĩ»
    -0.08
    åĬłæĭ¿å¤§
    -0.08
    åħĭç¦ı
    -0.08
    ehme
    -0.08
    ä¸įåı¯æĢĿè®®
    -0.08
    lassen
    -0.08
    aix
    -0.08
    ç®Ģ缴
    -0.08
    POSITIVE LOGITS
    åįķ纯çļĦ
    0.10
    lessly
    0.09
    ç¨ĭ度ä¸Ĭ
    0.09
    åľ°æĬĬ
    0.08
    èĢĮå·²
    0.08
    st
    0.08
    çŁŃçŁŃçļĦ
    0.08
    åı¯æĥľäºĨ
    0.08
    å±ĢéĻIJäºİ
    0.07
    åįķ纯
    0.07
    Activations Density 0.021%

    No Known Activations