© 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. 24602
    Prev
    Next
    INDEX
    Explanations

    Jones, Tigers, Eagles, Philadelphia

    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
    å±ı
    -0.06
    I
    -0.06
    èĩ´
    -0.06
    æ®ĭ
    -0.06
    _comp
    -0.06
    éĢļè¿ĩ
    -0.06
    ucc
    -0.06
    ba
    -0.06
    ^{
    -0.06
    weit
    -0.06
    POSITIVE LOGITS
    -License
    0.09
    iany
    0.09
    antung
    0.08
    áÄį
    0.08
    ."&
    0.08
     mesti
    0.08
    [unit
    0.08
    -awesome
    0.08
    etas
    0.08
    istán
    0.07
    Activations Density 0.003%

    No Known Activations