© 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. 59878
    Prev
    Next
    INDEX
    Explanations

    absolute

    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
    ï¾Ł
    -0.09
    dale
    -0.08
    ftar
    -0.08
    lac
    -0.08
    ings
    -0.08
    aybe
    -0.08
    иг
    -0.08
    mediately
    -0.08
    appropri
    -0.07
    æīĢä»¥ä½ł
    -0.07
    POSITIVE LOGITS
    itude
    0.09
    æĦıä¹īä¸ĬçļĦ
    0.09
    ì§ĵ
    0.07
    OLUTE
    0.07
     sayıda
    0.07
    lication
    0.07
    ìĭľíĶ¼
    0.06
    stin
    0.06
    ounc
    0.06
    mente
    0.06
    Activations Density 0.011%

    No Known Activations