© 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. 21559
    Prev
    Next
    INDEX
    Explanations

    is, are, assumptions

    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
     ìļ´ìĺģíķĺê³ł
    -0.06
    æĹłåĬŁ
    -0.06
     Reflex
    -0.05
    Two
    -0.05
    isu
    -0.05
    çľĭä¾Ĩ
    -0.05
    ia
    -0.05
    rio
    -0.05
    رس
    -0.05
    “
    -0.05
    POSITIVE LOGITS
    çĶ
    0.07
    лад
    0.06
    éĹ°
    0.06
    abor
    0.06
    วิà¸Ļ
    0.06
    åķ°
    0.06
    неÑģ
    0.06
    æľĢæł¹æľ¬
    0.05
    大èĩªçĦ¶çļĦ
    0.05
    ä¸įåıª
    0.05
    Activations Density 0.034%

    No Known Activations