© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21077
    Prev
    Next
    INDEX
    Explanations

    floating point errors

    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
    稿
    -0.09
    .asc
    -0.09
    ราà¸ļ
    -0.08
    aÅĤ
    -0.08
    ignor
    -0.07
    NotFoundException
    -0.07
     sza
    -0.07
    ogn
    -0.07
    çĶ¨å¿ĥåİ»
    -0.07
     scu
    -0.07
    POSITIVE LOGITS
    è¿Ļæĺ¯çĶ±äºİ
    0.08
     slight
    0.08
    IOS
    0.06
    è¿IJç®Ĺ
    0.06
    Ñĩки
    0.06
    ä¸įåı¯éģ¿åħįçļĦ
    0.06
    ikos
    0.06
     residual
    0.06
    åĨ¶
    0.06
    æ´¥
    0.06
    Activations Density 0.019%

    No Known Activations