© 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. 19717
    Prev
    Next
    INDEX
    Explanations

    .

    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
    ularity
    -0.05
    æ½ĩæ¹ĺ
    -0.05
    ç¬¬åĽĽæĿ¡
    -0.05
    clusive
    -0.05
    åĽĽæĸ¹
    -0.05
     задолженноÑģÑĤи
    -0.05
    ű
    -0.05
    æľŁä¸Ń
    -0.05
    æķ£
    -0.05
     nếp
    -0.05
    POSITIVE LOGITS
    usas
    0.06
    ché
    0.06
    grave
    0.06
    å±ħæ°ij身份è¯ģ
    0.06
    emez
    0.06
    corso
    0.05
    Alive
    0.05
    ذاÙĥ
    0.05
    ÃŃb
    0.05
    ufact
    0.05
    Activations Density 0.002%

    No Known Activations