© 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. 18187
    Prev
    Next
    INDEX
    Explanations

    ending in -ment, -ful, -able, -edly, -al

    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
    ê¹IJ
    -0.09
    åıªåı¯æĥľ
    -0.08
    errer
    -0.08
    ÙijÙĩ
    -0.08
    ãģĨãģ¡ãģ«
    -0.08
    ISCO
    -0.08
    ìį¨
    -0.08
    Ùijت
    -0.07
    satz
    -0.07
    sst
    -0.07
    POSITIVE LOGITS
    ment
    0.10
    ingly
    0.10
    lessly
    0.09
    ful
    0.08
    fully
    0.08
    ably
    0.08
    able
    0.08
    mann
    0.08
    edly
    0.08
    al
    0.07
    Activations Density 1.077%

    No Known Activations