© 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. 22186
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    ien
    -0.05
    ____________
    -0.05
    ________
    -0.05
    _
    -0.05
    âĢ¢
    -0.05
    imon
    -0.05
    ingat
    -0.04
    Picture
    -0.04
    ____
    -0.04
    è¯Ŀ说
    -0.04
    POSITIVE LOGITS
    åĪĨæŀIJä¸İ
    0.07
    åħ¬èĭ±
    0.07
    度çļĦ
    0.06
    icales
    0.06
    度é«ĺ
    0.06
    boro
    0.06
    étique
    0.06
    ãĤ¹ãĥĪãĥ¼ãĥ«
    0.06
     ucz
    0.06
    bakan
    0.06
    Activations Density 0.010%

    No Known Activations