© 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. 34553
    Prev
    Next
    INDEX
    Explanations

    mathematical context involving fractions

    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¦Ĥ约
    -0.07
    ads
    -0.06
    ower
    -0.06
    mark
    -0.06
     literally
    -0.06
    fa
    -0.06
    olum
    -0.06
    åıįèĢĮæĺ¯
    -0.06
     deem
    -0.06
     minus
    -0.06
    POSITIVE LOGITS
    ç¾ħæĸ¯
    0.08
    èļ¤
    0.07
    atria
    0.07
    ÄĽk
    0.07
    èĬŃèķ¾èĪŀ
    0.07
    inki
    0.07
    èľĴ
    0.07
    ername
    0.07
    ermann
    0.07
    lek
    0.07
    Activations Density 0.010%

    No Known Activations