© 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. 18032
    Prev
    Next
    INDEX
    Explanations

    in this paper

    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
     disent
    -0.06
    æıIJéĨĴä½ł
    -0.06
    theless
    -0.06
    åĪ¹
    -0.06
    ula
    -0.06
    indsay
    -0.06
    laubt
    -0.06
     ÙĪÙİع
    -0.06
    èĺ¿
    -0.06
    ERE
    -0.06
    POSITIVE LOGITS
    çĸµ
    0.05
    æĬĢæľ¯ä¸İ
    0.05
    æĹłçijķ
    0.05
    ipc
    0.04
    amed
    0.04
    é¡į
    0.04
    sic
    0.04
    vias
    0.04
    Plug
    0.04
    ä»ĸ们认为
    0.04
    Activations Density 0.075%

    No Known Activations