© 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. 21602
    Prev
    Next
    INDEX
    Explanations

    to [noun]

    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
    姥
    -0.06
    edet
    -0.06
     Howe
    -0.06
    еÑĢна
    -0.06
    æķĻèĤ²æĺ¯
    -0.06
    ìĬ¨
    -0.05
    éĹ®é¢ĺæķ´æĶ¹
    -0.05
    èĬ±ä¸Ģ
    -0.05
    .aw
    -0.05
    æĸĩç«łäºĨ
    -0.05
    POSITIVE LOGITS
    ä»ħæľī
    0.06
    éĻ·
    0.05
    ä¸İåİŁ
    0.05
    åıĪä¸į
    0.05
    ÑħÑĥд
    0.05
    Rec
    0.05
    Ùĥر
    0.05
     неб
    0.05
    缺ä¹ı
    0.05
    iss
    0.05
    Activations Density 0.022%

    No Known Activations