© 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. 17735
    Prev
    Next
    INDEX
    Explanations

    I may ask

    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
    formes
    -0.07
    holt
    -0.07
    ebra
    -0.07
    alda
    -0.07
    æij¸åºķ
    -0.06
    leston
    -0.06
    æĮł
    -0.06
    iated
    -0.06
    à¸Ńà¸ļ
    -0.06
    (scale
    -0.06
    POSITIVE LOGITS
    unix
    0.05
    åIJį
    0.05
    awk
    0.05
    åıĸå¾Ĺ
    0.05
     Dun
    0.05
     F
    0.05
     unw
    0.05
    éĩĩåıĸ
    0.05
    ude
    0.05
     Mi
    0.05
    Activations Density 0.002%

    No Known Activations