© 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. 48368
    Prev
    Next
    INDEX
    Explanations

    ring-opening polymerization, addition, displacement

    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
    æĿŁ
    -0.09
    indle
    -0.07
    åĪĪ
    -0.07
    beam
    -0.07
    åħĨ
    -0.07
    éĩı
    -0.07
    oons
    -0.06
    æĿŁæīĭ
    -0.06
    家åºŃåĴĮ
    -0.06
    æĸ¯èĴĤ
    -0.06
    POSITIVE LOGITS
    á»ģn
    0.08
    XHR
    0.08
    ersh
    0.08
    ReturnType
    0.07
    水表
    0.07
     résol
    0.07
    yam
    0.07
    /rem
    0.07
     inversion
    0.07
    resses
    0.07
    Activations Density 0.008%

    No Known Activations