© 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. 19679
    Prev
    Next
    INDEX
    Explanations

    cart, chart, size, duration

    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
    onica
    -0.07
    é«ĺè°ĥ
    -0.06
     Perempuan
    -0.06
    Ñĥже
    -0.06
    inado
    -0.06
    zak
    -0.06
    ãģĹãģ¦ãĤĤãĤīãģĪãĤĭ
    -0.06
    ziata
    -0.06
    дÑĬÑĢжа
    -0.06
    fam
    -0.06
    POSITIVE LOGITS
    æĮĩ
    0.05
    çļĦæĺ¯
    0.05
     conservative
    0.05
    åıĹ
    0.05
    0.05
    åħĪåľ¨
    0.05
    1
    0.05
    ä¼į
    0.04
    arli
    0.04
    r
    0.04
    Activations Density 0.012%

    No Known Activations