© 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. 17343
    Prev
    Next
    INDEX
    Explanations

    prosthetic devices and eyewear

    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
     unprotected
    -0.08
    æ¸ħçĻ½
    -0.07
     spontan
    -0.07
     abund
    -0.07
     indef
    -0.07
    guarded
    -0.07
     lit
    -0.07
     protected
    -0.07
    åĸ·æ³ī
    -0.07
    avax
    -0.06
    POSITIVE LOGITS
     snug
    0.11
     worn
    0.10
    èĪĴéĢĤ度
    0.09
     wearer
    0.09
    佩æĪ´
    0.09
    èĪĴéĢĤ
    0.09
     ì°©ìļ©
    0.08
     adjustable
    0.08
     customized
    0.08
    å®ļåĪ¶
    0.08
    Activations Density 0.102%

    No Known Activations