© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30187
    Prev
    Next
    INDEX
    Explanations

    React, Qt, football, C++

    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
    '
    -0.07
    åĩ½
    -0.06
    ÑĮ
    -0.06
    åľ¨ä¸Ģå®ļç¨ĭ度ä¸Ĭ
    -0.06
    ariah
    -0.06
    *
    -0.06
    éĺĻ
    -0.05
    luit
    -0.05
    orsch
    -0.05
    OR
    -0.05
    POSITIVE LOGITS
    leter
    0.09
    rowable
    0.08
    berra
    0.08
     tamp
    0.08
    srv
    0.08
    æĵħ
    0.08
     afili
    0.08
    dna
    0.08
    ìĹIJìĦł
    0.08
    зим
    0.08
    Activations Density 0.001%

    No Known Activations