© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20568
    Prev
    Next
    INDEX
    Explanations

    Dosa, grilled, basil

    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
    нÑıÑĤ
    -0.06
    硬æľĹ
    -0.06
    ä¸įçŁ¥éģĵä½ł
    -0.06
    zw
    -0.06
    ä¸Ģåı£æ°Ķ
    -0.05
    ider
    -0.05
    éĿłå±±
    -0.05
    ç®Ģç®Ģåįķ
    -0.05
    irement
    -0.05
    Modern
    -0.05
    POSITIVE LOGITS
    çī¡ä¸¹
    0.06
    è¯Ń
    0.06
    解
    0.05
    æıı
    0.05
     destructor
    0.05
    æįķ
    0.05
    å¾ģ
    0.05
    è¨Ģ
    0.05
    lecht
    0.05
    ãģµãĤĭ
    0.05
    Activations Density 0.025%

    No Known Activations