© 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. 24032
    Prev
    Next
    INDEX
    Explanations

    cellular functions and maintenance

    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
    লà§ĩà¦ĸ
    -0.07
    åįķèĸĦ
    -0.07
    ukti
    -0.07
     Calon
    -0.07
    \\/
    -0.07
    çĿ«æ¯Ľ
    -0.07
    è¿ŀèĥľ
    -0.07
     upfront
    -0.07
    èĢ³èģĭ
    -0.07
    å°Ĩè¾¾
    -0.07
    POSITIVE LOGITS
     pH
    0.09
     vital
    0.09
     functions
    0.09
    æıIJä¾ĽåIJĦç§į
    0.08
    è°ĥæݧ
    0.08
     Functions
    0.08
    丰å¯Įå¤ļ彩
    0.08
     activities
    0.08
    çĸĨ
    0.08
    åĬŁèĥ½çļĦ
    0.08
    Activations Density 0.047%

    No Known Activations