© 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. 63680
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and conjunctions

    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
    anes
    -0.08
    太éĥİ
    -0.07
    ë¦Ħ
    -0.07
    ual
    -0.07
    ang
    -0.07
     lname
    -0.07
    cko
    -0.06
    èĴ
    -0.06
    nl
    -0.06
    à®ļà¯įà®ļ
    -0.06
    POSITIVE LOGITS
    è¿Ļ个æķ°åŃĹ
    0.10
    åºŀ大
    0.09
    åºŀ大çļĦ
    0.08
    åĽĽåįĥ
    0.08
    åħŃçĻ¾
    0.08
    hammer
    0.08
     immense
    0.07
    atge
    0.07
    isses
    0.07
    ä¹ĭ大
    0.07
    Activations Density 0.128%

    No Known Activations