© 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. 25084
    Prev
    Next
    INDEX
    Explanations

    break points and transitions

    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
    اÙģÛĮ
    -0.08
    cesa
    -0.07
    ¥
    -0.07
    ceso
    -0.07
    anzas
    -0.07
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.07
     Páginas
    -0.07
    okok
    -0.07
    ĵ¨
    -0.07
    orsa
    -0.07
    POSITIVE LOGITS
    常è§Ħ
    0.08
    åį´æĹłæ³ķ
    0.08
     applicable
    0.08
    常è§ĦçļĦ
    0.08
    éĥ½æĹłæ³ķ
    0.08
    ä¸įéĢĤçĶ¨
    0.08
    èĻ½çĦ¶æľī
    0.07
    ä¹ŁæĹłæ³ķ
    0.07
    æĹłæ³ķ
    0.07
     nonexistent
    0.07
    Activations Density 0.158%

    No Known Activations