© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4894
    Prev
    Next
    INDEX
    Explanations

    voice heard or voice features

    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
    Negative Logits
    ĺ
    -0.09
     vreme
    -0.08
    หมาย
    -0.07
    ìĤ¬íķŃ
    -0.07
    arian
    -0.07
    ãĤ¥
    -0.07
    หมายà¸Ħวาม
    -0.07
    Ĺ
    -0.07
    ï¸ı
    -0.06
    -ish
    -0.06
    POSITIVE LOGITS
    ulpt
    0.10
    fulness
    0.09
    borne
    0.09
    lessly
    0.08
    less
    0.08
    åĪļèIJ½
    0.08
     веÑĤÑĢа
    0.08
    keeping
    0.08
    bok
    0.08
    åĴĮæ°Ķ
    0.08
    Activations Density 0.028%

    No Known Activations