© 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. 19355
    Prev
    Next
    INDEX
    Explanations

    with followed by description

    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
    ursa
    -0.06
    inya
    -0.06
    ģ
    -0.06
    .collect
    -0.06
    æıIJéĨĴ大家
    -0.06
    ÄĽj
    -0.06
    åĵģãģ®
    -0.06
    Å¡ten
    -0.06
    å®ļçļĦ
    -0.06
    enis
    -0.06
    POSITIVE LOGITS
    Âł
    0.05
    azza
    0.05
    soever
    0.05
    ÑīеÑģÑĤв
    0.05
     Beard
    0.05
     trá»Ŀi
    0.05
    ster
    0.05
    ancock
    0.04
    оÑĢод
    0.04
    诸
    0.04
    Activations Density 0.062%

    No Known Activations