© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 41879
    Prev
    Next
    INDEX
    Explanations

    remainder when divided by

    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
    ause
    -0.08
    /front
    -0.07
    æĶ¾æħ¢
    -0.06
    饮
    -0.06
     drinks
    -0.06
    æĭĽåij¼
    -0.06
    åĸĿçļĦ
    -0.06
    front
    -0.06
     Flüss
    -0.06
    è£ħæ½¢
    -0.06
    POSITIVE LOGITS
    å¹Ĥ
    0.08
     Cipher
    0.08
    ä½Ļ
    0.08
    inox
    0.08
    ilog
    0.08
    ponent
    0.07
    WithValue
    0.07
    едÑĭ
    0.07
    bacher
    0.07
     claves
    0.07
    Activations Density 0.009%

    No Known Activations