© 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. 49972
    Prev
    Next
    INDEX
    Explanations

    compound mathematical expressions

    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
    edet
    -0.09
    åįĹéĺ³
    -0.08
    ç§ijæĬĢåѦéĻ¢
    -0.08
    емÑĭ
    -0.08
    大计
    -0.08
    })();
    -0.08
    ä¸Ģåıij
    -0.07
    lore
    -0.07
    velt
    -0.07
    _TRY
    -0.07
    POSITIVE LOGITS
    0.07
    0.06
    atan
    0.06
    .....
    0.06
     epic
    0.06
    åħ¬éģĵ
    0.06
    çīĪæĿĥ
    0.06
    è¿İ
    0.06
    onte
    0.05
    åħ°
    0.05
    Activations Density 0.033%

    No Known Activations