© 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. 48095
    Prev
    Next
    INDEX
    Explanations

    math expressions with variables

    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
    eppe
    -0.08
    AndWait
    -0.08
    obod
    -0.07
    athi
    -0.07
    adder
    -0.07
     Usta
    -0.07
    rip
    -0.07
    hic
    -0.07
    èĢĮèĩªå·±
    -0.07
    anium
    -0.06
    POSITIVE LOGITS
     íķĺëĤĺëĬĶ
    0.08
    ettore
    0.08
    人已
    0.08
    äººä¹Ł
    0.07
    βά
    0.07
     íķĺëĤĺê°Ģ
    0.07
    ç³»ç»Łæĺ¯
    0.07
    uyen
    0.07
    ervi
    0.06
    ect
    0.06
    Activations Density 0.018%

    No Known Activations