© 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. 25956
    Prev
    Next
    INDEX
    Explanations

    closing brackets followed by FirstName

    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
    airo
    -0.09
    _eof
    -0.07
    weets
    -0.06
    é¯ĸ
    -0.06
     PACKET
    -0.06
    merc
    -0.06
     Eleg
    -0.06
    ¯
    -0.06
    zi
    -0.06
     }:
    -0.06
    POSITIVE LOGITS
    opr
    0.08
     Kontra
    0.08
     XXL
    0.07
    ardia
    0.07
     fran
    0.07
    aksa
    0.07
    ldata
    0.07
    orre
    0.07
    bris
    0.07
     experienced
    0.07
    Activations Density 0.010%

    No Known Activations