© 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. 21013
    Prev
    Next
    INDEX
    Explanations

    referenced therein

    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
    ìłĦíĺķ
    -0.07
    ä¸įå¾Ĺå·²
    -0.07
    trup
    -0.07
    undy
    -0.07
    æľ¬ç«ĻåĨħ容
    -0.07
    æľī家
    -0.07
    geg
    -0.07
    iou
    -0.07
    åIJĪæ³ķçļĦ
    -0.07
    æľĢèµ·çłģ
    -0.07
    POSITIVE LOGITS
    ç«ĭåĬŁ
    0.07
    沿éĿ©
    0.07
     referenced
    0.07
    åį«åĽ½
    0.06
    hoff
    0.06
    èįIJ
    0.06
    Digest
    0.06
    ustus
    0.06
     newer
    0.06
    rien
    0.06
    Activations Density 0.090%

    No Known Activations