© 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. 21174
    Prev
    Next
    INDEX
    Explanations

    .com

    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
    ils
    -0.07
    éĢĹ
    -0.06
    ør
    -0.06
     ad
    -0.06
    rie
    -0.06
    åĶ¤
    -0.06
    pane
    -0.06
    Ñģпа
    -0.06
    æīĢåľ¨
    -0.06
    Ñģан
    -0.06
    POSITIVE LOGITS
    acus
    0.06
     же
    0.05
    ost
    0.05
    女ç¥ŀ
    0.05
    å§Ĩæĸ¯
    0.05
    cup
    0.05
    ç¥ŀ
    0.05
     Scholarship
    0.05
    大ä¹ī
    0.05
     whereby
    0.05
    Activations Density 0.001%

    No Known Activations