© 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. 43504
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols

    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
     applic
    -0.07
    Ïĥη
    -0.07
    çĭ¬
    -0.07
    {}.
    -0.07
    ordan
    -0.07
     <<=
    -0.07
    thora
    -0.07
    /../
    -0.07
     Applic
    -0.07
    缴å±ŀ
    -0.06
    POSITIVE LOGITS
    æĪIJæīį
    0.09
    mand
    0.08
    å¼ģ
    0.08
    atrix
    0.07
    oty
    0.06
    pace
    0.06
    éĿĴå·ŀ
    0.06
    å½ĵå¿ĥ
    0.06
    enni
    0.06
    åĩ«
    0.06
    Activations Density 0.003%

    No Known Activations