© 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. 59823
    Prev
    Next
    INDEX
    Explanations

    `static` followed by `float` or `void`

    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
    fertig
    -0.07
    dien
    -0.07
    frei
    -0.06
    ä¸Ļ
    -0.06
    lander
    -0.06
    iert
    -0.06
    ìĭľìķĦ
    -0.06
    adi
    -0.06
     rein
    -0.06
     GIVEN
    -0.06
    POSITIVE LOGITS
    åīį款
    0.08
    unia
    0.08
    æ²³éķĩ
    0.08
    arnya
    0.08
    apkan
    0.08
    íĺ¹
    0.07
    unya
    0.07
    å£ķ
    0.07
    ptomon
    0.07
    á»±c
    0.07
    Activations Density 0.074%

    No Known Activations