© 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. 20409
    Prev
    Next
    INDEX
    Explanations

    shapes and drawing

    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
    ahoo
    -0.07
    Âł
    -0.07
    ager
    -0.07
    ä¸Ģ天çļĦ
    -0.06
    ng
    -0.06
    åĿĩæĿ¥èĩª
    -0.06
    å¤ļæīį
    -0.06
     all
    -0.06
    dependence
    -0.06
    ä»Ĭ天çļĦ
    -0.06
    POSITIVE LOGITS
    è§Ħ模为
    0.10
     ÑĢазмеÑĢом
    0.09
    è§Ħ模
    0.09
    æŶéļĶ
    0.09
    nade
    0.08
     emlék
    0.08
    è§Ħ模æľĢ大
    0.08
    å®Įæķ´åľ°
    0.08
     overlapping
    0.08
    лко
    0.08
    Activations Density 0.014%

    No Known Activations