© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19589
    Prev
    Next
    INDEX
    Explanations

    needs

    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
    hurst
    -0.06
    æ¯ı次éĥ½
    -0.06
    ä¸įæĪIJ
    -0.06
    踪影
    -0.06
    软ç»Ħç»ĩ
    -0.06
    æĿ¾å¼Ľ
    -0.05
    纨
    -0.05
    gel
    -0.05
    olt
    -0.05
    felt
    -0.05
    POSITIVE LOGITS
    czeÅĽ
    0.06
     اشت
    0.06
     Na
    0.06
    æĿ¥è®¡ç®Ĺ
    0.06
    Na
    0.06
    åĭĺ
    0.05
     bi
    0.05
     поÑĤÑĢебноÑģÑĤи
    0.05
    æµģåIJij
    0.05
    _transition
    0.05
    Activations Density 0.006%

    No Known Activations