© 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. 20575
    Prev
    Next
    INDEX
    Explanations

    business models

    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
    å®īåħ¨çŁ¥è¯Ĩ
    -0.08
    eldon
    -0.08
    åķĨåѦéĻ¢
    -0.08
    mare
    -0.08
    arit
    -0.08
    个ä¸įåģľ
    -0.08
    æĽ´çĶŁ
    -0.07
    skal
    -0.07
    åİĨåı²è®°å½ķ
    -0.07
    è§ĦåĪĴå±Ģ
    -0.07
    POSITIVE LOGITS
    åıĺéĿ©
    0.10
     Change
    0.09
     change
    0.08
    éĿ©åij½
    0.08
    éĿ©åij½çļĦ
    0.08
    change
    0.08
    ç»ĵæŀĦ
    0.08
    ä¸Ĭå±Ĥ
    0.08
    Change
    0.07
     Revolutionary
    0.07
    Activations Density 0.012%

    No Known Activations