© 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. 20769
    Prev
    Next
    INDEX
    Explanations

    rare aortic arch

    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
    itek
    -0.07
    è¡ĮåĬ¨ä¸Ń
    -0.07
    彤
    -0.06
    /cop
    -0.06
    .adjust
    -0.06
    adius
    -0.06
     Legs
    -0.06
    ieno
    -0.06
    çĶ³è¯·æī§è¡Į
    -0.06
    æĢ»è¦ģ
    -0.06
    POSITIVE LOGITS
    rare
    0.10
    èĻ½çĦ¶åľ¨
    0.09
    æŀģå°ij
    0.09
     rare
    0.08
     rarely
    0.08
    irian
    0.08
     Rare
    0.08
    ç½ķ
    0.08
    Rare
    0.08
    ç½ķè§ģ
    0.08
    Activations Density 0.022%

    No Known Activations