© 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. 40603
    Prev
    Next
    INDEX
    Explanations

    Championship login details

    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
    ergestellt
    -0.10
    Scaler
    -0.08
    ificate
    -0.08
    eldorf
    -0.08
    chiere
    -0.08
    ucas
    -0.08
    ambu
    -0.08
    acle
    -0.07
    cott
    -0.07
    corre
    -0.07
    POSITIVE LOGITS
    æľĢåIJİæĺ¯
    0.07
     Lastly
    0.07
    pto
    0.07
    omu
    0.06
    Finally
    0.06
    ptic
    0.06
    çļĦæľĢåIJİ
    0.06
    Lastly
    0.06
     finally
    0.06
    bur
    0.06
    Activations Density 0.001%

    No Known Activations