© 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. 42664
    Prev
    Next
    INDEX
    Explanations

    speaking softly or whispering

    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
    æķĻèĤ²ç½ij
    -0.09
    ä¸ĢåĽ¾
    -0.08
    CodeGen
    -0.07
    缸åħ³éĺħ读
    -0.07
    antan
    -0.07
    COPE
    -0.07
     flagr
    -0.07
    tä
    -0.07
    оÑģÑĤав
    -0.07
    大éĺµ
    -0.07
    POSITIVE LOGITS
    æĸŃç»Ń
    0.10
     voice
    0.10
     Voice
    0.09
    voice
    0.09
    Voice
    0.09
     whisper
    0.09
     whispered
    0.08
     spoken
    0.08
    éŁ³éĩı
    0.08
    äºĨä¸Ģåı¥
    0.08
    Activations Density 0.041%

    No Known Activations