© 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. 18973
    Prev
    Next
    INDEX
    Explanations

    después

    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
    ãĤĵ
    -0.05
    åĬĽåĴĮ
    -0.05
    swagen
    -0.05
    smith
    -0.05
    aute
    -0.05
    technik
    -0.05
    ãĤĵãģ®
    -0.05
    plin
    -0.05
    ات
    -0.05
    ìķ¼
    -0.05
    POSITIVE LOGITS
    ych
    0.07
    amente
    0.07
    alus
    0.07
    éĩĩ访æĹ¶è¡¨ç¤º
    0.07
    èĢĮéĻį
    0.07
    cere
    0.07
    ä»Ĺ
    0.07
    ÑĩеÑĤ
    0.07
    æŃ¢æŃ¥
    0.07
    ails
    0.06
    Activations Density 0.002%

    No Known Activations