© 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. 20170
    Prev
    Next
    INDEX
    Explanations

    citations and references

    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
    ç»į
    -0.07
    æķ°éĩı为
    -0.06
    anzo
    -0.06
    ongi
    -0.06
    zun
    -0.05
    çĸĨ
    -0.05
    зм
    -0.05
    æķ°éĩı
    -0.05
    ihar
    -0.05
    ovsky
    -0.05
    POSITIVE LOGITS
    件
    0.06
     tạm
    0.05
    elv
    0.05
    alni
    0.05
    miss
    0.05
    ç¹ģ
    0.05
    e
    0.05
    æ»´æ»´
    0.05
    uddy
    0.05
    件çļĦ
    0.05
    Activations Density 0.016%

    No Known Activations