© 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. 18848
    Prev
    Next
    INDEX
    Explanations

    knitting and crochet

    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
    æ¿
    -0.06
    äºļ
    -0.06
    centes
    -0.06
    ابÙĬØ©
    -0.06
    çĥ¤é¸Ń
    -0.06
    æī¬åŃIJ
    -0.06
    ارÙĩ
    -0.06
    ä¸įè¦ģè½»æĺĵ
    -0.06
    æ³
    -0.06
    راط
    -0.06
    POSITIVE LOGITS
    æį»
    0.06
    ç¼ĸç»ĩ
    0.06
     Halt
    0.06
     stitch
    0.05
     strand
    0.05
    åľĪåľĪ
    0.05
     hello
    0.05
    ç¨Ģçĸı
    0.05
     weaving
    0.05
     knitting
    0.05
    Activations Density 0.028%

    No Known Activations