© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21605
    Prev
    Next
    INDEX
    Explanations

    words preceding frequency markers

    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
    สวà¸Ļ
    -0.06
    ç¨Ģ
    -0.06
    à¹ģà¸ķà¹Ī
    -0.06
    ä½Ĩæĺ¯ä¸Ģ
    -0.06
    Immutable
    -0.06
     verdade
    -0.06
     inm
    -0.05
    kens
    -0.05
    Thu
    -0.05
    æĭŁ
    -0.05
    POSITIVE LOGITS
    ous
    0.05
     Bey
    0.05
    ided
    0.05
     Assurance
    0.05
    adal
    0.05
    lectric
    0.05
    anes
    0.05
    cmd
    0.05
    nett
    0.05
     assure
    0.05
    Activations Density 0.001%

    No Known Activations