© 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. 13822
    Prev
    Next
    INDEX
    Explanations

    reaction time task

    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
     maybe
    -0.07
     Blasio
    -0.07
     reserves
    -0.07
     perhaps
    -0.06
    achinery
    -0.06
    åķ¸
    -0.06
    translator
    -0.06
    perhaps
    -0.06
    æ£
    -0.06
    igrations
    -0.06
    POSITIVE LOGITS
     stimuli
    0.11
    诱åıij
    0.09
     stimulus
    0.09
     пÑĢедÑĬÑı
    0.09
     cue
    0.09
    åĪºæ¿ĢçļĦ
    0.09
    éĻĮçĶŁ
    0.08
     cues
    0.08
    åĪºæ¿Ģ
    0.08
     task
    0.08
    Activations Density 0.318%

    No Known Activations