© 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. 42490
    Prev
    Next
    INDEX
    Explanations

    practical action and actionable insights

    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
    å®Įæķ´çīĪ
    -0.08
    å¿ħçŃĶ
    -0.08
    ìĹŃìĿĦ
    -0.08
    åĽłåħ¬
    -0.08
     overall
    -0.07
    çIJĨæīĢ
    -0.07
    éĢīæĭ©ä¸įåIJĮçļĦ
    -0.07
    skim
    -0.07
    eke
    -0.07
    ä¸Ńå¤ĸ
    -0.07
    POSITIVE LOGITS
     actionable
    0.12
    izable
    0.10
     konkret
    0.10
    æĬĵæīĭ
    0.10
     practical
    0.09
    åĪĩå®ŀåı¯è¡ĮçļĦ
    0.09
    åı¯è¡ĮçļĦ
    0.09
    åħ·ä½ĵçļĦ
    0.09
    isable
    0.09
    æĵįä½ľæĢ§
    0.09
    Activations Density 0.033%

    No Known Activations