© 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. 18728
    Prev
    Next
    INDEX
    Explanations

    food ingredients and dishes

    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
    æĪĸä¸į
    -0.06
    æģµ
    -0.06
     ÙĨب
    -0.06
    atau
    -0.05
    inq
    -0.05
    ail
    -0.05
    æŃ»æŃ»
    -0.05
     or
    -0.05
    appel
    -0.05
     mù
    -0.05
    POSITIVE LOGITS
    贯穿
    0.06
    ifat
    0.06
     sustitu
    0.06
     beden
    0.06
    å¾Ģ
    0.06
    ,eg
    0.06
    BSD
    0.06
    ears
    0.06
     поÑĤе
    0.06
    ì£¼ë¡ľ
    0.06
    Activations Density 0.027%

    No Known Activations