© 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. 57285
    Prev
    Next
    INDEX
    Explanations

    Herbig, DC DVDs, Altorfer, Butler Garage, Kartis

    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
    ä¸į顺
    -0.07
    åĢ
    -0.06
    åĴĮè¡Į为
    -0.06
    åĪĨéĩı
    -0.06
     Fonseca
    -0.06
    æ¯Ķæ¯Ķ
    -0.06
    .easy
    -0.06
     Publicada
    -0.06
    æij¹
    -0.06
    æĻļè¾Ī
    -0.06
    POSITIVE LOGITS
     appunto
    0.09
    izzi
    0.08
    話說
    0.08
    ä¹ĭ为
    0.08
     daÃŃ
    0.08
    ç³»åĪĹ产åĵģ
    0.08
     stesso
    0.07
     tersendiri
    0.07
    initely
    0.07
    缸åħ³éĹ®çŃĶ
    0.07
    Activations Density 0.358%

    No Known Activations