© 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. 22640
    Prev
    Next
    INDEX
    Explanations

    question is

    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
     therefore
    -0.11
     however
    -0.10
    åĽłæѤ
    -0.10
     thus
    -0.09
    however
    -0.09
    åĽłèĢĮ
    -0.09
     deshalb
    -0.09
    åĽłæŃ¤åľ¨
    -0.09
     toutefois
    -0.08
    ãģĿãģ®ãģŁãĤģ
    -0.08
    POSITIVE LOGITS
    igli
    0.09
    å¼¥
    0.08
     ((((
    0.07
     conclude
    0.07
    okens
    0.07
    å¾Ĺåĩºç»ĵ论
    0.07
    angkan
    0.07
    ovina
    0.07
    acons
    0.07
     concludes
    0.07
    Activations Density 0.065%

    No Known Activations