© 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. 47960
    Prev
    Next
    INDEX
    Explanations

    cube root, power of

    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
    éĻĨ
    -0.09
     brû
    -0.08
    lange
    -0.07
     mend
    -0.07
     crossings
    -0.07
    aros
    -0.07
    plr
    -0.07
    aray
    -0.07
    oldt
    -0.07
     scissors
    -0.07
    POSITIVE LOGITS
    ucht
    0.08
     cub
    0.07
    éĿĴäºij
    0.07
    sein
    0.06
    usable
    0.06
     Primer
    0.06
    ض
    0.06
    (so
    0.06
    ä¸Ģäºĭ
    0.06
    åĴĮæĢĿèĢĥ
    0.06
    Activations Density 0.004%

    No Known Activations