© 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. 20380
    Prev
    Next
    INDEX
    Explanations

    generalizations and summaries

    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
    ich
    -0.06
    imuth
    -0.06
    icher
    -0.06
    ег
    -0.06
    atu
    -0.06
    bek
    -0.06
    brand
    -0.05
    æ´¥
    -0.05
    knowledge
    -0.05
    iento
    -0.05
    POSITIVE LOGITS
    loquent
    0.05
    æĿī
    0.05
    æĮīä¸Ģä¸ĭ
    0.05
     Wiley
    0.05
    åĪļåĪļ好
    0.05
     fl
    0.05
    åĩĨç¡®æĢ§åĴĮåIJĪæ³ķæĢ§
    0.05
    تÙĬÙĨ
    0.05
    éºĴ
    0.05
    ebet
    0.05
    Activations Density 0.004%

    No Known Activations