© 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. 33310
    Prev
    Next
    INDEX
    Explanations

    estimator, decoder, coding, algorithms, contracts

    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
    _literals
    -0.08
    ä¸īè¿ŀ
    -0.07
     contracted
    -0.07
    rijk
    -0.07
     contiguous
    -0.07
    _compat
    -0.07
    udere
    -0.07
    NotEmpty
    -0.07
    å¦ĤæŀľæĤ¨çļĦ
    -0.07
    amu
    -0.07
    POSITIVE LOGITS
    åĨ³çŃĸ
    0.09
     Ney
    0.08
     optim
    0.08
    æĶ¹è¿Ľ
    0.08
     decisions
    0.08
    ä»»
    0.08
    æĺ¯åŁºäºİ
    0.08
     decision
    0.08
    ceb
    0.08
    åŁºäºİ
    0.07
    Activations Density 0.027%

    No Known Activations