© 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. 30671
    Prev
    Next
    INDEX
    Explanations

    KK, OR, *, “-

    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
    dek
    -0.09
    osat
    -0.08
    çģ«ä¸Ĭ
    -0.08
    inho
    -0.08
    enfant
    -0.08
    ñez
    -0.08
    bach
    -0.08
    æľ¬é¢ĺçŃĶæ¡Ī
    -0.07
    chini
    -0.07
    åıijæĦģ
    -0.07
    POSITIVE LOGITS
    管çIJĨåıĬ
    0.06
    管çIJĨçŃī
    0.06
    Time
    0.06
    alaman
    0.06
    жами
    0.06
    æĬĢæľ¯çŃī
    0.05
    姨
    0.05
     Buen
    0.05
     áp
    0.05
    ä½ıçļĦ
    0.05
    Activations Density 0.014%

    No Known Activations