© 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. 56469
    Prev
    Next
    INDEX
    Explanations

    less than or insufficient

    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
     Canonical
    -0.08
    奶çĪ¸
    -0.07
    å¢ŀæķĪ
    -0.07
    æѤä¸Ģ
    -0.07
    ä¸įåħ¥
    -0.07
    oty
    -0.07
    cial
    -0.06
     Halt
    -0.06
    æķ´æ²»å·¥ä½ľ
    -0.06
     odch
    -0.06
    POSITIVE LOGITS
    åĢŁ
    0.09
    è¶³å¤ŁçļĦ
    0.08
    èĤĥ
    0.08
    ä¸Ģ次æĢ§
    0.08
     shortage
    0.08
     total
    0.07
     available
    0.07
     MetroFramework
    0.07
     άν
    0.07
     suficiente
    0.07
    Activations Density 0.008%

    No Known Activations