© 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. 21899
    Prev
    Next
    INDEX
    Explanations

    you followed by a verb

    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
    ikel
    -0.07
    ness
    -0.07
    metic
    -0.06
    ئة
    -0.06
    notice
    -0.06
    nod
    -0.05
    äºİè¡Į
    -0.05
    bour
    -0.05
    ä¹ĭæĦı
    -0.05
    chenk
    -0.05
    POSITIVE LOGITS
    o
    0.08
    er
    0.08
    ing
    0.08
    æŃ¢
    0.07
    ed
    0.06
    oxy
    0.06
    ea
    0.06
    yl
    0.06
    y
    0.06
    Ìģ
    0.06
    Activations Density 0.019%

    No Known Activations