© 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. 50177
    Prev
    Next
    INDEX
    Explanations

    CIRCUIT and section numbers

    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
    áĥĵáĥĶ
    -0.08
    úb
    -0.08
    plits
    -0.08
    ä¸Ĭ大
    -0.08
    Ùĭ
    -0.08
    üd
    -0.08
    ctr
    -0.07
    åĸľæĢĴ
    -0.07
    æī«çłģåħ³æ³¨
    -0.07
    æķ°éĩıåĴĮ
    -0.07
    POSITIVE LOGITS
    åĴĮ第
    0.11
    ï¸ı
    0.09
    件äºĭ
    0.08
    èĩªå·±
    0.07
    -feira
    0.07
    èĩªçĦ¶æ®µ
    0.07
    çķª
    0.07
    OfWeek
    0.07
    äºĭéłħ
    0.06
    ය
    0.06
    Activations Density 0.009%

    No Known Activations