© 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. 34802
    Prev
    Next
    INDEX
    Explanations

    numbers, units, or comparisons

    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
    åį´æĹłæ³ķ
    -0.06
    chenk
    -0.06
     зав
    -0.06
     Initializes
    -0.06
    ÏĪε
    -0.06
    RO
    -0.06
    jö
    -0.06
    ERO
    -0.06
    åį´ä¸įèĥ½
    -0.06
     Origins
    -0.06
    POSITIVE LOGITS
    大æ¦Ĥåľ¨
    0.08
    æĪijè®°å¾Ĺ
    0.08
     interpol
    0.08
    Datas
    0.07
    اÙĦات
    0.07
    Interpolator
    0.07
    æŁ¥
    0.07
    /cache
    0.07
    .binding
    0.07
    ableObject
    0.07
    Activations Density 0.004%

    No Known Activations