© 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. 17407
    Prev
    Next
    INDEX
    Explanations

    Clothing, Tights

    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
     why
    -0.06
    为ä»Ģä¹Ī
    -0.06
    ose
    -0.05
    vera
    -0.05
    ot
    -0.05
    éľ²å¤©
    -0.05
    aja
    -0.05
    age
    -0.05
    è·Łä¸Ĭ
    -0.05
    Ïį
    -0.05
    POSITIVE LOGITS
    positor
    0.06
    hton
    0.06
    ementes
    0.05
     side
    0.05
     vars
    0.05
    ä¸įçŁ¥æīĢ
    0.05
    æł¼æł¼
    0.05
     prepar
    0.05
    ines
    0.05
    ighter
    0.05
    Activations Density 0.140%

    No Known Activations