© 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. 21808
    Prev
    Next
    INDEX
    Explanations

    development goals

    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
     parc
    -0.06
     Cool
    -0.05
    为äºĨæĽ´å¥½åľ°
    -0.05
     hữu
    -0.05
    æݧåĪ¶æĬĢæľ¯
    -0.05
    inner
    -0.05
    Kel
    -0.05
     T
    -0.05
    åĨ¬å¤©çļĦ
    -0.05
     stuff
    -0.05
    POSITIVE LOGITS
    åĪ¶èį¯æľīéĻIJåħ¬åı¸
    0.06
    zeit
    0.06
    itando
    0.06
    hid
    0.06
    åħ¼æĢ»ç»ıçIJĨ
    0.06
    ä¸Ģä¾ĭ
    0.05
    getDisplay
    0.05
    egram
    0.05
    edic
    0.05
    çħ©
    0.05
    Activations Density 0.008%

    No Known Activations