© 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. 21415
    Prev
    Next
    INDEX
    Explanations

    polynomials and functions

    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
    该åĮº
    -0.07
    óÅĤ
    -0.07
    erna
    -0.07
    LABEL
    -0.07
    ells
    -0.07
    ascar
    -0.07
    bdd
    -0.07
    ع
    -0.06
    ual
    -0.06
    ä¸ĬçļĦ讲è¯Ŀ
    -0.06
    POSITIVE LOGITS
     function
    0.08
    éĶĻä½į
    0.07
    unce
    0.07
    åĩ½æķ°
    0.07
    iscal
    0.07
    funktion
    0.07
    andes
    0.07
     unlocked
    0.07
    inance
    0.07
    avra
    0.07
    Activations Density 0.006%

    No Known Activations