© 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. 10343
    Prev
    Next
    INDEX
    Explanations

    electrostatic interactions

    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
    полне
    -0.08
    ftp
    -0.08
    ørs
    -0.07
    istributor
    -0.07
    -Za
    -0.07
    oard
    -0.07
    otec
    -0.07
    untr
    -0.07
    çļĨçŁ¥
    -0.07
    uest
    -0.07
    POSITIVE LOGITS
    å¦Ĥæŀľæľī
    0.09
     ìŀĪëĭ¤ë©´
    0.09
    çŃīåħ¶ä»ĸ
    0.08
    å¦Ĥæľī
    0.08
     somewhere
    0.08
    éļIJèĹıåľ¨
    0.08
    (if
    0.08
    åģĩ
    0.08
    -like
    0.08
    åŃĺåľ¨äºİ
    0.08
    Activations Density 0.071%

    No Known Activations