© 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. 50402
    Prev
    Next
    INDEX
    Explanations

    equivalent positions, type of, fate map, may be

    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
    สัà¸Ļ
    -0.08
    azzo
    -0.08
    ätz
    -0.08
    atten
    -0.07
    åħ³éĶ®çݯèĬĤ
    -0.07
    åįłéģĵ
    -0.07
    peen
    -0.07
    è¯Ī
    -0.07
    ä»»ãģĽ
    -0.07
    undu
    -0.07
    POSITIVE LOGITS
     symmetry
    0.08
    活泼
    0.08
    enant
    0.08
     accessibility
    0.07
    yed
    0.07
    ALLEL
    0.07
    äºĮçŃī
    0.07
     exchange
    0.07
    /access
    0.07
     groups
    0.06
    Activations Density 0.003%

    No Known Activations