© 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. 20616
    Prev
    Next
    INDEX
    Explanations

    separate or distinct concepts

    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
    eto
    -0.06
    pps
    -0.06
    tribute
    -0.06
    ollo
    -0.06
    ests
    -0.05
     prih
    -0.05
    amon
    -0.05
    .gz
    -0.05
    éĻĦä¸Ĭä¸Ģ
    -0.05
    uries
    -0.05
    POSITIVE LOGITS
     separate
    0.10
    çĭ¬ç«ĭ
    0.09
    ä¸įåIJĮ
    0.08
     seperate
    0.08
     Separate
    0.08
    åIJĮä¸Ģ
    0.07
    different
    0.07
    éĩįåıł
    0.07
     distinct
    0.07
    åIJĮä¸Ģ个
    0.07
    Activations Density 0.237%

    No Known Activations