© 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. 58382
    Prev
    Next
    INDEX
    Explanations

    executive functioning cognition

    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±ħæĺĵ
    -0.07
    plib
    -0.07
    .onView
    -0.07
    æĻ¶ç¡ħ
    -0.07
    èĬ¹
    -0.07
    ç¬Ļ
    -0.07
    讹
    -0.07
    å¨
    -0.07
    åŦ
    -0.07
    èĻļåģĩè®°è½½
    -0.07
    POSITIVE LOGITS
    æݧåĪ¶
    0.10
    èĩªæݧ
    0.09
    èĩªå¾ĭ
    0.09
    è°ĥæݧ
    0.09
     control
    0.09
    æݧåĪ¶çļĦ
    0.09
     ì¡°ìłĪ
    0.09
    èĩªåĪ¶
    0.09
    -control
    0.09
     regulation
    0.08
    Activations Density 0.037%

    No Known Activations