© 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. 30944
    Prev
    Next
    INDEX
    Explanations

    min read

    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
    æ¨
    -0.09
    ropa
    -0.08
    engi
    -0.08
    пÑĢаве
    -0.08
    geist
    -0.08
    åħ¨ä½ĵå¹²éĥ¨èģĮå·¥
    -0.08
     daycare
    -0.08
    为æĤ¨æݨèįIJ
    -0.08
    akaran
    -0.08
    weer
    -0.08
    POSITIVE LOGITS
    ons
    0.08
    onte
    0.07
    arena
    0.06
    leter
    0.06
    æĭħå¿ĥçļĦ
    0.06
     C
    0.06
    éĿĴäºij
    0.06
    udo
    0.06
    ä¸īçĶ²
    0.06
     Pear
    0.06
    Activations Density 0.039%

    No Known Activations