© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19534
    Prev
    Next
    INDEX
    Explanations

    we all

    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
     prev
    -0.06
    AME
    -0.05
    çĶŁåij½
    -0.05
    ame
    -0.05
    allel
    -0.05
    itas
    -0.05
    rying
    -0.05
     Prev
    -0.05
    çļĦçĶŁåij½
    -0.05
    èĩªçĦ¶æĺ¯
    -0.05
    POSITIVE LOGITS
    rott
    0.07
    æĹ¥èµ·èĩ³
    0.06
    avic
    0.06
     humili
    0.06
    levance
    0.06
    este
    0.06
     timed
    0.06
     Ire
    0.06
    iha
    0.06
    ocard
    0.06
    Activations Density 0.021%

    No Known Activations