© 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. 38256
    Prev
    Next
    INDEX
    Explanations

    propose new methods and techniques

    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
    æİĴæ³Ħ
    -0.07
    enville
    -0.07
    æŃ£å¸¸
    -0.07
    符åIJĪåĽ½å®¶
    -0.07
    æ°¸ä¹ħ
    -0.07
    å¤ļç±³
    -0.07
    æ°¸ä¹ħæĢ§
    -0.07
    estr
    -0.07
     sortable
    -0.07
    æİĴåĩº
    -0.06
    POSITIVE LOGITS
     techniques
    0.14
     algorithms
    0.14
     methods
    0.12
     methodologies
    0.11
     Techniques
    0.10
     models
    0.10
    methods
    0.10
     Algorithms
    0.10
     applied
    0.10
     algorithm
    0.10
    Activations Density 0.217%

    No Known Activations