© 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. 17801
    Prev
    Next
    INDEX
    Explanations

    URLs, thank you, license

    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
    iles
    -0.06
     {}:
    -0.06
    审
    -0.05
    çıĤ
    -0.05
     паÑĤо
    -0.05
     acted
    -0.05
    ungkan
    -0.05
    ç»ıèIJ¥æ´»åĬ¨
    -0.05
    å«£
    -0.05
    juk
    -0.05
    POSITIVE LOGITS
    æ¯ıéĢ¢
    0.05
    åŁİå¸Ĥä¸Ń
    0.05
    姿
    0.05
    atomic
    0.05
    arten
    0.05
     обÑĢе
    0.05
    订åĪ¶
    0.05
    缴è¾ĸå¸Ĥ
    0.05
    exact
    0.05
    æľīä¸įåIJĮ
    0.05
    Activations Density 0.002%

    No Known Activations