© 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. 21705
    Prev
    Next
    INDEX
    Explanations

    intravenous infusion or induction

    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
    ayos
    -0.07
    à¸Ńยà¹Īาà¸ĩà¹Ħมà¹Īà¸ĸูà¸ģà¸ķà¹īà¸Ńà¸ĩ
    -0.07
     annual
    -0.07
     trá
    -0.07
    åħijç¾İåħĥ
    -0.06
    annual
    -0.06
    initi
    -0.06
    /interface
    -0.06
    äten
    -0.06
     jähr
    -0.06
    POSITIVE LOGITS
    æģIJ
    0.05
    åĢĻ
    0.05
    abil
    0.05
    软
    0.05
    æł¸
    0.05
     appr
    0.05
    åIJIJåĩº
    0.05
    uet
    0.05
     V
    0.05
    ç¨ĭåºı
    0.05
    Activations Density 0.005%

    No Known Activations