© 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. 57601
    Prev
    Next
    INDEX
    Explanations

    verbs describing observations or actions

    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
    onge
    -0.07
    å®ĥæīĢ
    -0.07
    æīĢä»¥åľ¨
    -0.07
    å®ŀéªĮä¸Ń
    -0.06
    æ¹Ľ
    -0.06
    å®ĥéĤ£
    -0.06
    iban
    -0.06
    çĶ¨åľ¨
    -0.06
    å®ŀä¹łæľŁéĹ´
    -0.06
    ê²
    -0.06
    POSITIVE LOGITS
    eks
    0.09
     ÑĥÑĩаÑģÑĤием
    0.08
    ectu
    0.08
    åħ³éĶ®çݯèĬĤ
    0.08
    pora
    0.08
    óta
    0.08
    人äºĨ
    0.07
    à¸Ńะà¹Ħรà¸ļà¹īาà¸ĩ
    0.07
    elui
    0.07
    quo
    0.07
    Activations Density 0.139%

    No Known Activations