© 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. 9972
    Prev
    Next
    INDEX
    Explanations

    compound, diversified, fraction, amort, oriented

    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
    产åĵģä¸Ńå¿ĥ
    -0.08
    CDATA
    -0.08
    ipse
    -0.08
    rarian
    -0.08
    ä¸īå°º
    -0.08
     Aper
    -0.07
    è°ħ
    -0.07
    .argmax
    -0.07
    æ±Łè·¯
    -0.07
    ools
    -0.07
    POSITIVE LOGITS
    æ¤
    0.07
    åIJĮé¾Ħ
    0.07
    pt
    0.07
    è¶Ĭå¤ļ
    0.07
    /shared
    0.07
     Effect
    0.07
     effect
    0.07
    æĸ¹å¼ı为
    0.07
    Effect
    0.07
    pit
    0.06
    Activations Density 0.009%

    No Known Activations