© 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. 44860
    Prev
    Next
    INDEX
    Explanations

    file extensions or common code snippets

    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
    entication
    -0.08
    idity
    -0.07
    rence
    -0.07
    иÑĢов
    -0.07
    ÑĥÑİÑī
    -0.07
    ulant
    -0.07
    &lt
    -0.06
    rellas
    -0.06
    town
    -0.06
    reno
    -0.06
    POSITIVE LOGITS
    Ĥ
    0.10
    à§įস
    0.09
    izm
    0.09
    د
    0.09
     gái
    0.09
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    0.08
     vét
    0.08
    chemas
    0.08
    umeric
    0.08
    chein
    0.08
    Activations Density 0.124%

    No Known Activations