© 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. 63028
    Prev
    Next
    INDEX
    Explanations

    first to describe or explore

    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
    ught
    -0.08
    cedure
    -0.07
    å¤ļä¸ĩ
    -0.06
    çļĦä¸Ģç³»åĪĹ
    -0.06
    ½Ķ
    -0.06
     erne
    -0.06
    许å¤ļçļĦ
    -0.06
     sogar
    -0.06
    åł¡åŀĴ
    -0.06
    NullOr
    -0.06
    POSITIVE LOGITS
    çĦ¶å¤§
    0.09
    çĦ¶æĺ¯
    0.09
    phan
    0.08
    alon
    0.08
    æ±ĤçĶŁåŃĺ
    0.08
    好ä¸į
    0.08
    ادÙĩ
    0.07
    éĥ¨å°±
    0.07
     dulu
    0.07
    æ¸Ī
    0.07
    Activations Density 0.001%

    No Known Activations