© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20138
    Prev
    Next
    INDEX
    Explanations

    1

    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
    è¡ĮèĢħ
    -0.07
    iego
    -0.07
    é¢Ħæ¡Ī
    -0.06
    ä¸Ģå®ļéĩıçļĦ
    -0.06
    ä¸įåºĶæ±Ĥ
    -0.06
    qli
    -0.06
    æī¬çļĦ
    -0.06
    ecat
    -0.06
    æıļ
    -0.06
    åIJİèĢħ
    -0.06
    POSITIVE LOGITS
    's
    0.05
    uber
    0.05
    ÙĩÛĮ
    0.05
    ke
    0.05
    L
    0.05
    ��
    0.05
     institucional
    0.05
     Ñģебе
    0.05
     bal
    0.05
    بة
    0.05
    Activations Density 0.019%

    No Known Activations