© 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. 14358
    Prev
    Next
    INDEX
    Explanations

    lack, neglect, uncommon, low

    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
    ä¸įä¸Ģå®ļ
    -0.07
     uncont
    -0.07
     flawless
    -0.07
     safely
    -0.07
    ä¸Ģå®ļä¸įèĥ½
    -0.07
     eleg
    -0.07
     impeccable
    -0.07
     Maire
    -0.07
    ä¸įåı¯æĬĹ
    -0.06
     unavoidable
    -0.06
    POSITIVE LOGITS
    缺ä¹ı
    0.13
     lack
    0.11
     lacks
    0.11
    缺å°ij
    0.10
     despite
    0.10
    lack
    0.10
     lacked
    0.10
     lacking
    0.10
    æ¬łç¼º
    0.09
    èĻ½çĦ¶æľī
    0.09
    Activations Density 0.575%

    No Known Activations