© 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. 55746
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with sqrt

    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
    æºIJçļĦ
    -0.07
    пÑĢÑı
    -0.07
    /lg
    -0.07
    _lineno
    -0.07
    ELLOW
    -0.06
    omnia
    -0.06
    mgr
    -0.06
    âĢ¦]
    -0.06
    UMP
    -0.06
    æĶ»éĺ²
    -0.06
    POSITIVE LOGITS
    ç¢į
    0.07
    άÏģÏĩ
    0.07
    两年
    0.07
     uncomment
    0.07
    olong
    0.07
    ÑĥÑĩ
    0.06
    ç±³
    0.06
    æĹłæĥħçļĦ
    0.06
    ĵĴ
    0.06
    æŃ£æľ¬
    0.06
    Activations Density 0.005%

    No Known Activations