© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42115
    Prev
    Next
    INDEX
    Explanations

    Georgia court cases

    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
    erts
    -0.06
     Barber
    -0.06
     poss
    -0.06
    æīĢè°ĵ
    -0.06
    çħ§çĽ¸
    -0.06
    scha
    -0.06
    IDER
    -0.06
    vious
    -0.06
    wo
    -0.06
    忽çĦ¶
    -0.06
    POSITIVE LOGITS
    æĸ¹æ¡ĪåĴĮ
    0.08
    åİ»ä½ķ
    0.08
     yourself
    0.08
     ê²ĥìĿ´ê³ł
    0.08
     yourselves
    0.08
    ãĤĴçµĮãģ¦
    0.07
    è§ĦåĪĴå±Ģ
    0.07
    请åħĪ
    0.07
    ιά
    0.07
    året
    0.07
    Activations Density 0.017%

    No Known Activations