© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18545
    Prev
    Next
    INDEX
    Explanations

    dates and image labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦä¸į
    -0.06
    sver
    -0.05
    æĻļå®ī
    -0.05
    ä¸įåIJĪçIJĨ
    -0.05
    æĪ³
    -0.05
    åĬłæ³¨
    -0.05
    uart
    -0.05
    room
    -0.05
    ä¸ĢäºĮ
    -0.05
     frustra
    -0.05
    POSITIVE LOGITS
     вз
    0.06
    ÑģобÑĭ
    0.06
    以轻
    0.05
    åıĬ以ä¸ĭ
    0.05
    代夫
    0.05
    tern
    0.05
     brute
    0.05
    请éĢīæĭ©
    0.05
    êt
    0.05
     switch
    0.05
    Activations Density 0.015%

    No Known Activations