© 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. 18279
    Prev
    Next
    INDEX
    Explanations

    .child, .childData, childSnapshot

    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
    irman
    -0.06
    æŶéĹ´ä¸º
    -0.06
    å¹´å¹´åºķ
    -0.06
    æĢ§ä»¥åıĬ
    -0.06
    ä»ĸè§īå¾Ĺ
    -0.06
    ä¹łè¿ijå¹³æĢ»ä¹¦è®°åħ³äºİ
    -0.05
    äºijå±±
    -0.05
    éķ¿çº¦
    -0.05
    åĦª
    -0.05
    ogi
    -0.05
    POSITIVE LOGITS
    ’d
    0.05
    ool
    0.05
    ä¸ĭæĭī
    0.05
    ERM
    0.05
    èĪĴæľį
    0.05
    erno
    0.05
     пÑĢоб
    0.05
    ño
    0.05
    olding
    0.05
    ^
    0.05
    Activations Density 0.078%

    No Known Activations