© 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. 39095
    Prev
    Next
    INDEX
    Explanations

    research study 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
    åľ¨æĸ°çļĦä¸Ģå¹´éĩĮ
    -0.07
    çļĦéĤ£ä¸ª
    -0.06
    ungan
    -0.06
    rezza
    -0.06
    çľĭåĪ°ä¸Ģ个
    -0.06
    æľªå°½
    -0.06
    åľ¨æ°´éĩĮ
    -0.06
     ((_
    -0.06
     apprec
    -0.06
    éĤ£å¤´
    -0.06
    POSITIVE LOGITS
     randomly
    0.10
     blinded
    0.10
     underwent
    0.09
    æ¯ıç»Ħ
    0.09
     varying
    0.08
    åIJĦç»Ħ
    0.08
     subjected
    0.08
     RANDOM
    0.08
     Random
    0.08
     jeweils
    0.08
    Activations Density 1.530%

    No Known Activations