© 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. 49661
    Prev
    Next
    INDEX
    Explanations

    coupe

    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
    请æĮī
    -0.07
    çļĦæŀĹ
    -0.06
    ron
    -0.06
    od
    -0.06
    onic
    -0.06
     un
    -0.06
    天å¿ĥ
    -0.06
     rep
    -0.06
    ken
    -0.06
    fw
    -0.05
    POSITIVE LOGITS
    ISTA
    0.09
    ož
    0.08
    entifier
    0.08
     aterr
    0.08
     beis
    0.08
    alfa
    0.08
    administrator
    0.07
    æĬĬ
    0.07
    `.`
    0.07
    umerator
    0.07
    Activations Density 0.004%

    No Known Activations