© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21888
    Prev
    Next
    INDEX
    Explanations

    cyborg, cybernetic

    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
    gl
    -0.06
    isku
    -0.06
     genera
    -0.05
     Digit
    -0.05
     provision
    -0.05
    quet
    -0.05
    建设ä¸İ
    -0.05
    æį§
    -0.05
    ä¸İåºĶçĶ¨
    -0.05
     Trustees
    -0.05
    POSITIVE LOGITS
    çIJĨå·¥åѦéĻ¢
    0.06
    ä¹ī
    0.06
    è¡Ģ液循çݯ
    0.06
    çļĦç²¾
    0.06
    RAIN
    0.06
    би
    0.06
    cision
    0.05
     exchanged
    0.05
    Exchange
    0.05
    ä¹Łç§°
    0.05
    Activations Density 0.003%

    No Known Activations