© 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. 18212
    Prev
    Next
    INDEX
    Explanations

    para definir

    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
    ...
    -0.07
    o
    -0.06
    /
    -0.06
    aan
    -0.06
    ab
    -0.06
    er
    -0.06
    pt
    -0.06
    u
    -0.05
    го
    -0.05
    aad
    -0.05
    POSITIVE LOGITS
    สà¸Ļิà¸Ĺ
    0.07
    beste
    0.07
    (es
    0.07
    ugas
    0.07
    ugt
    0.07
    ÑģÑĤан
    0.07
    landen
    0.07
    æ¯Ķäºļ
    0.07
    جاÙħ
    0.07
    ÙĪات
    0.06
    Activations Density 0.001%

    No Known Activations