© 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. 18230
    Prev
    Next
    INDEX
    Explanations

    nipples, cape, plays, wild

    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
    è¾ħåĬ©
    -0.05
    è§Ħ磩
    -0.05
    éģ¿åħįåĩºçİ°
    -0.05
    çļĦä¹łæĥ¯
    -0.05
    è¾ħ
    -0.05
     formatted
    -0.05
    æł¼éĩĮ
    -0.05
    è¾Ļ
    -0.05
    æŃ£è½¨
    -0.05
    æ»ļ
    -0.05
    POSITIVE LOGITS
    ær
    0.06
    embl
    0.06
    为天
    0.06
    OMP
    0.06
    fut
    0.05
    emp
    0.05
    autos
    0.05
    eté
    0.05
    ادت
    0.05
    SSF
    0.05
    Activations Density 0.003%

    No Known Activations