© 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. 56683
    Prev
    Next
    INDEX
    Explanations

    Km, Kd, Ki, affinity

    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
    arch
    -0.08
     Conti
    -0.08
    alj
    -0.08
    å¦ĤçĶ»
    -0.08
    Ø·Ùħ
    -0.08
    nei
    -0.08
    imei
    -0.08
    cke
    -0.08
    ä¸įåı¯åIJ¦è®¤
    -0.07
    à¸Ĭà¸Ļ
    -0.07
    POSITIVE LOGITS
    ickle
    0.07
    æĭ
    0.07
    ensitivity
    0.07
    éħ¸
    0.06
    ä½İèĩ³
    0.06
     ëĤ®
    0.06
    sweet
    0.06
    ikli
    0.06
    xin
    0.06
    饥饿
    0.06
    Activations Density 0.027%

    No Known Activations