© 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. 23567
    Prev
    Next
    INDEX
    Explanations

    export statements and object definitions

    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
    åĴĮé¼ĵåĬ±
    -0.06
    apolis
    -0.06
    ä¾Ŀæ³ķ
    -0.06
    Assoc
    -0.06
    ervis
    -0.06
    undy
    -0.06
    anon
    -0.06
     tis
    -0.06
    ycastle
    -0.06
    onn
    -0.06
    POSITIVE LOGITS
    LEASE
    0.08
    igans
    0.08
    符
    0.07
    engen
    0.07
    ç¶
    0.07
    marsh
    0.07
    çĻ¾èĪ¬
    0.07
    ä¸Ĭä¸Ģç«ł
    0.07
    å»·
    0.07
    rière
    0.07
    Activations Density 0.047%

    No Known Activations