© 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. 39524
    Prev
    Next
    INDEX
    Explanations

    correctness or errors

    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
     apapun
    -0.08
    åĬłåĭĴ
    -0.08
    åİ»ä½ķ
    -0.08
    çļĦä¸Ģç±»
    -0.07
    unter
    -0.07
    whatever
    -0.07
    å¥īä¸Ĭ
    -0.07
     ÐĿика
    -0.07
    çģ«çĥŃçļĦ
    -0.07
    ä¸įåı¯æĢĿè®®
    -0.07
    POSITIVE LOGITS
    TRUE
    0.08
    å±ŀäºİ
    0.07
     TRUE
    0.07
    羣æŃ£
    0.07
    羣æŃ£åľ°
    0.07
     correct
    0.07
    (s
    0.06
    æĹ¢æĺ¯
    0.06
    羣æŃ£çļĦ
    0.06
     NOT
    0.06
    Activations Density 0.023%

    No Known Activations