© 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. 12846
    Prev
    Next
    INDEX
    Explanations

    fractions and numbers

    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
    vi
    -0.07
    dee
    -0.07
    ante
    -0.07
    jur
    -0.07
    wich
    -0.07
    och
    -0.07
    תר
    -0.06
    fadeOut
    -0.06
    Trail
    -0.06
    jä
    -0.06
    POSITIVE LOGITS
    aksin
    0.08
    паÑĢ
    0.08
    åŃ
    0.07
     Lek
    0.07
    porn
    0.07
    DMETHOD
    0.07
    æ¹ĸ滨
    0.07
    å¤ĩ
    0.07
    agher
    0.06
    _RULE
    0.06
    Activations Density 0.001%

    No Known Activations