© 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. 29400
    Prev
    Next
    INDEX
    Explanations

    comparative, glut, comparable, year, H, JP, CG, pgsql, electro

    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
    èĥĮä¸Ĭ
    -0.07
    asten
    -0.07
    ÅĽc
    -0.06
    çī©åĴĮ
    -0.06
    并èĮĤ
    -0.06
    æľªå°½
    -0.06
    diag
    -0.06
    å´½
    -0.06
    ÅĤos
    -0.06
    æİĸ
    -0.06
    POSITIVE LOGITS
    0.09
    osan
    0.08
    绣
    0.07
    éĢļè¾½
    0.07
    æ³Ĭ
    0.07
    ãĥŃãĥĥãĤ¯
    0.07
    ujo
    0.07
    aup
    0.07
    etul
    0.07
    æĭ¾
    0.07
    Activations Density 0.269%

    No Known Activations