© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46534
    Prev
    Next
    INDEX
    Explanations

    truthness verification

    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
    viare
    -0.07
    ssue
    -0.07
    ãĤ¤ãĥ«
    -0.07
     invece
    -0.07
     instead
    -0.07
    auj
    -0.07
    æĪijå¿ĥ
    -0.06
    rol
    -0.06
    ogo
    -0.06
     eas
    -0.06
    POSITIVE LOGITS
     BUT
    0.08
    ä½ĨåIJĮæŶ
    0.08
    ä½Ĩå¦Ĥæŀľ
    0.08
    çĴĢ
    0.08
     Worth
    0.08
    ä½Ĩæĺ¯å¯¹äºİ
    0.08
    ä½Ĩçİ°åľ¨
    0.07
    æĮ¯
    0.07
    akov
    0.07
     cá»ijt
    0.07
    Activations Density 0.034%

    No Known Activations