© 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. 44199
    Prev
    Next
    INDEX
    Explanations

    dedicated to creating about

    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
    ALTH
    -0.09
    ASM
    -0.08
    ä¸Ńåħ³æĿij
    -0.07
    ean
    -0.07
    ìĩĦ
    -0.07
    esian
    -0.07
    ä¸ĢæľĿ
    -0.07
    ående
    -0.07
    ech
    -0.07
    çĻ»å½ķæŁ¥çľĭ
    -0.07
    POSITIVE LOGITS
    elin
    0.07
    åįİå±±
    0.07
    '><
    0.06
    Cod
    0.06
    -script
    0.05
     übrigens
    0.05
    欢è¿İ大家éĺħ读
    0.05
    yyÉĻ
    0.05
    éī
    0.05
    bility
    0.05
    Activations Density 1.322%

    No Known Activations