© 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. 31377
    Prev
    Next
    INDEX
    Explanations

    joint service, coupled equations, lists, arrays

    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
    (ca
    -0.07
    åħ¨ä½ĵåħļåijĺ
    -0.07
    ListItem
    -0.07
    istant
    -0.07
     capita
    -0.07
    ç¼¥
    -0.07
    .wr
    -0.07
    arra
    -0.07
    个好
    -0.07
    æķ´æķ°
    -0.06
    POSITIVE LOGITS
    秣
    0.08
    衬
    0.08
    èģĶåIJĪ
    0.07
    uggy
    0.07
    matched
    0.07
    ä¸ī家
    0.07
    ä¸įåıij
    0.07
    紧贴
    0.07
    ahas
    0.07
    å§ĵ
    0.07
    Activations Density 0.049%

    No Known Activations