© 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. 49889
    Prev
    Next
    INDEX
    Explanations

    subgroup, extracted, page, view

    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
     mans
    -0.07
    zio
    -0.07
    ë©Ģ
    -0.07
    æµĬ
    -0.07
    route
    -0.07
    kest
    -0.07
    å®ŀçī©
    -0.07
    äumen
    -0.06
    kais
    -0.06
    ?type
    -0.06
    POSITIVE LOGITS
    çĭ¬ç«ĭæĢ§
    0.09
    çĭ¬ç«ĭ
    0.09
    çĭ¬ç«ĭçļĦ
    0.09
    çį¨ç«ĭ
    0.08
    çªģåĩºçļĦ
    0.08
     extracted
    0.08
    åľ¨å½ĵåľ°
    0.08
     ëıħ립
    0.08
     inherits
    0.08
    èĩªæ²»
    0.08
    Activations Density 0.035%

    No Known Activations