© 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. 56108
    Prev
    Next
    INDEX
    Explanations

    corretti

    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
    ä¼´çĿĢ
    -0.08
    croft
    -0.07
    妬
    -0.07
    legate
    -0.06
     raccom
    -0.06
     Quinn
    -0.06
    obox
    -0.06
    ç¥Ŀ
    -0.06
    (kv
    -0.06
    çļĦæīĭæ³ķ
    -0.06
    POSITIVE LOGITS
    éĴ»
    0.08
    èĬ¸
    0.08
    æ¦Ľ
    0.07
    çĮ®èº«
    0.07
    udir
    0.07
    /contact
    0.07
    ãĥ¼ãĤ¸ãĥ¼
    0.07
    个ä½ĵçļĦ
    0.07
    cpy
    0.07
    abad
    0.07
    Activations Density 0.505%

    No Known Activations