© 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. 40027
    Prev
    Next
    INDEX
    Explanations

    hypothetical arrangements or structures

    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
    моÑĤ
    -0.08
     Online
    -0.07
    iegel
    -0.07
    ambi
    -0.07
    éģĩä¸Ĭ
    -0.07
     ONLINE
    -0.07
    以赴
    -0.07
     Sonn
    -0.07
    tees
    -0.07
     Cached
    -0.07
    POSITIVE LOGITS
     somehow
    0.09
    æŁIJç§į
    0.08
     hypothetical
    0.08
    zl
    0.07
    åıªæıIJä¾Ľ
    0.07
     infinitely
    0.07
     magically
    0.07
     mechanism
    0.07
    å°Ķæĸ¯
    0.07
     fixed
    0.07
    Activations Density 0.016%

    No Known Activations