© 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. 28404
    Prev
    Next
    INDEX
    Explanations

    catalyst complexes

    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
    ASCII
    -0.07
    åĩĿ
    -0.07
     justific
    -0.06
     Termo
    -0.06
    åĪĴæĭ¨
    -0.06
     scientifically
    -0.06
    éĽ¹
    -0.06
    å¿ħæľī
    -0.06
    çİ»
    -0.06
    æ®ĸ
    -0.06
    POSITIVE LOGITS
    uster
    0.09
    EMPL
    0.09
    activ
    0.09
    оÑģо
    0.08
     disclosed
    0.08
    Activ
    0.08
     catalyst
    0.08
    adle
    0.08
    ç»ĵæŀĦä¸İ
    0.08
    /debug
    0.08
    Activations Density 0.041%

    No Known Activations