© 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. 21891
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names

    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
    conde
    -0.06
    ÙIJÙħ
    -0.06
     تعا
    -0.06
    zeit
    -0.06
     fascin
    -0.05
    ugs
    -0.05
    æ´»åĬ¨çŃī
    -0.05
    ãģĦãģĦãģ®ãģĭ
    -0.05
     enr
    -0.05
    áĥ¬
    -0.05
    POSITIVE LOGITS
     euth
    0.05
    åıĸ款
    0.05
    IRECT
    0.05
    uwe
    0.05
     vong
    0.05
     ÐĶаÑĤ
    0.05
    ราà¸ĩ
    0.05
    aker
    0.05
    æ¯Ļ
    0.05
    å¦Ĥå±±
    0.05
    Activations Density 0.009%

    No Known Activations