© 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. 47323
    Prev
    Next
    INDEX
    Explanations

    spinal cord injury

    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
    irr
    -0.10
    ercial
    -0.09
    åĨł
    -0.09
    EDE
    -0.09
    é¬ĵ
    -0.09
    erras
    -0.08
    èĤ¡éª¨å¤´
    -0.08
    ekor
    -0.08
    ertools
    -0.08
    anson
    -0.08
    POSITIVE LOGITS
    å±ĢéĻIJ
    0.06
    å±ĢéĻIJæĢ§
    0.06
    çĺ«çĹª
    0.06
    æľ«ç«¯
    0.06
    èĦĬé«ĵ
    0.06
    大åݦ
    0.06
     master
    0.06
    çļĦåĬ¨çī©
    0.06
     br
    0.06
    cim
    0.06
    Activations Density 0.042%

    No Known Activations