© 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. 62672
    Prev
    Next
    INDEX
    Explanations

    greener; modulation speed

    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
     IQ
    -0.08
     cum
    -0.07
     Infer
    -0.06
    геÑĢ
    -0.06
     bid
    -0.06
    ka
    -0.06
    IDD
    -0.06
     organ
    -0.06
    lands
    -0.06
    IQ
    -0.06
    POSITIVE LOGITS
    ãģ©ãģ¡ãĤīãĤĤ
    0.09
    è¿Ļ两ç§į
    0.09
    两èĢħ
    0.09
    å°ĶèĴĻ
    0.09
    åħ©èĢħ
    0.08
    yal
    0.08
    è¿Ļ两
    0.08
    并举
    0.08
    _through
    0.08
    gesellschaft
    0.07
    Activations Density 0.260%

    No Known Activations