© 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. 17240
    Prev
    Next
    INDEX
    Explanations

    list view adapter

    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
    andid
    -0.06
    olla
    -0.06
    otence
    -0.06
    tele
    -0.06
    å·¥åħ·
    -0.06
    pren
    -0.06
    å·¥åħ·çļĦ
    -0.06
    _processors
    -0.06
    ruc
    -0.06
    ç«£
    -0.06
    POSITIVE LOGITS
    رÙĬØŃ
    0.06
    槽
    0.06
    ève
    0.05
     finger
    0.05
    åľ°éĵģ
    0.05
    çļĦæĸ°é²ľ
    0.05
    à¹ģ
    0.05
     Greenwood
    0.05
    loff
    0.05
    çļĦä¸ĭ
    0.05
    Activations Density 0.133%

    No Known Activations