© 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
    2. Qwen3.5-4B
    3. 15-RES-MATRYOSHKA-65K
    4. 17178
    Prev
    Next
    INDEX
    Explanations

    lists of numbers 1, 2, 3, 4

    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
    ingly
    -0.06
     báºŃc
    -0.06
     pä
    -0.06
     olacak
    -0.06
    ostal
    -0.05
     ÙħÙĦØŃ
    -0.05
    erah
    -0.05
    гÑĢа
    -0.05
    bjerg
    -0.05
    ä¹ĭåŁİ
    -0.05
    POSITIVE LOGITS
    toy
    0.05
     Lut
    0.05
    åĢĻ
    0.05
    çŃīåĨħ容
    0.05
     supp
    0.05
    .']
    0.05
    æ´¾
    0.05
    .);
    0.05
    alkan
    0.05
    .";
    0.05
    Activations Density 0.006%

    No Known Activations