© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14593
    Prev
    Next
    INDEX
    Explanations

    singer-songwriter, violinist, actor

    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
    <![
    -0.08
     supermer
    -0.07
     appunto
    -0.06
    è¿Ŀåıįä¸Ĭè¿°
    -0.06
    çĶļèĩ³åľ¨
    -0.06
    çĪªåŃIJ
    -0.06
    renz
    -0.06
    ä¹İ
    -0.06
    .orig
    -0.06
    éĻ¡çĦ¶
    -0.06
    POSITIVE LOGITS
    vs
    0.07
     woes
    0.07
    _vs
    0.07
    ï¼Ĩ
    0.07
    enor
    0.06
     coeur
    0.06
     âĢ¦.
    0.06
     childs
    0.06
    æŁ¥çľĭæĽ´å¤ļ
    0.06
    éĥ½æľīåĵªäºĽ
    0.06
    Activations Density 0.168%

    No Known Activations