© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11849
    Prev
    Next
    INDEX
    Explanations

    toilet placement

    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
    QE
    -0.07
    kB
    -0.07
    rika
    -0.07
    entas
    -0.07
    çļĦæIJŃéħį
    -0.07
     überzeugt
    -0.07
    arem
    -0.07
    æŀ
    -0.07
    AL
    -0.06
    æĽ²
    -0.06
    POSITIVE LOGITS
    ihar
    0.07
    abwe
    0.07
    еÑģÑĤво
    0.06
    eso
    0.06
     Som
    0.06
    梨èĬ±
    0.06
    atan
    0.06
    iers
    0.06
    lö
    0.06
    estelle
    0.06
    Activations Density 0.330%

    No Known Activations