© 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. 20819
    Prev
    Next
    INDEX
    Explanations

    begin by or start by

    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
    åħ¶ä¸Ńä¸Ģ个
    -0.06
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.06
    o
    -0.05
    ا
    -0.05
     Manufact
    -0.05
    rific
    -0.05
    ese
    -0.05
    ä¾ĭå¦Ĥ
    -0.05
    appropri
    -0.05
    orrow
    -0.05
    POSITIVE LOGITS
    èĢ³é¼»
    0.07
    æĬ±
    0.06
    tól
    0.06
    yt
    0.06
    hi
    0.06
    åĬĽå£«
    0.06
    eval
    0.06
    ÑģÑĤоиÑĤ
    0.06
    ä¸İæľ¬
    0.06
    تÙĪÙĨ
    0.06
    Activations Density 0.003%

    No Known Activations