© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20981
    Prev
    Next
    INDEX
    Explanations

    i've tried setInterval

    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
    aminh
    -0.06
    irth
    -0.06
    iffe
    -0.06
    omini
    -0.06
    occhi
    -0.06
    æĹłè¾¹
    -0.05
     Reci
    -0.05
    peci
    -0.05
     기ìĤ¬
    -0.05
    æ¿Ĵ临
    -0.05
    POSITIVE LOGITS
    isa
    0.07
    æ·±åħ¥
    0.06
    ä¸ĩ
    0.06
    avi
    0.05
    داÙĨ
    0.05
    æĻ¯
    0.05
    åħ§
    0.05
    è°ĥåĴĮ
    0.05
    éĻĦ
    0.05
     average
    0.05
    Activations Density 0.032%

    No Known Activations