© 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. 18900
    Prev
    Next
    INDEX
    Explanations

    true if, true else

    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
    atto
    -0.08
     Blasio
    -0.07
    ewise
    -0.07
    mr
    -0.07
    atti
    -0.07
    åĩºèº«çļĦ
    -0.07
    ments
    -0.07
    Chooser
    -0.07
    umba
    -0.07
    è°Īä¸įä¸Ĭ
    -0.07
    POSITIVE LOGITS
    /false
    0.10
    åķ¡
    0.07
    heit
    0.07
    zcze
    0.07
    /disable
    0.07
    häuser
    0.07
    hi
    0.06
    oader
    0.06
    hoot
    0.06
    false
    0.06
    Activations Density 0.028%

    No Known Activations