© 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. 18702
    Prev
    Next
    INDEX
    Explanations

    richness and enrichment

    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
    iente
    -0.06
    ç¾ļ
    -0.06
    orris
    -0.06
    ä¸ĢæĹģ
    -0.05
    æģ¯
    -0.05
     tille
    -0.05
    ëħķ
    -0.05
    ilton
    -0.05
    пли
    -0.05
    ä¸įçĪ½
    -0.05
    POSITIVE LOGITS
    ely
    0.07
    anei
    0.06
    uisse
    0.06
    annel
    0.06
    sver
    0.06
    HEL
    0.06
    å¢ĥçķĮ
    0.05
    ä¸Ģ个大
    0.05
     columns
    0.05
    zen
    0.05
    Activations Density 0.008%

    No Known Activations