© 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. 55230
    Prev
    Next
    INDEX
    Explanations

    to followed by 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
    [][
    -0.07
    agger
    -0.07
     sang
    -0.07
    éļıç¼ĺ
    -0.07
    ân
    -0.06
    å¼Ģ课
    -0.06
    宫å¤ĸ
    -0.06
    ายà¹Ģà¸Ľà¹ĩà¸Ļ
    -0.06
    est
    -0.06
    anga
    -0.06
    POSITIVE LOGITS
    Õ«Õ¶
    0.07
    aios
    0.07
    é¼İé¼İ
    0.07
    ç¡
    0.07
    ilhar
    0.07
    ird
    0.07
    veld
    0.07
    çŃł
    0.07
    ctors
    0.06
    INLINE
    0.06
    Activations Density 0.003%

    No Known Activations