© 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. 19582
    Prev
    Next
    INDEX
    Explanations

    number formatting and separators

    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
    ç³»
    -0.05
    åį¡è¥¿
    -0.05
     cos
    -0.05
    ç§ī
    -0.05
     hash
    -0.05
    Express
    -0.05
     orbital
    -0.05
     express
    -0.05
     bang
    -0.04
    1
    -0.04
    POSITIVE LOGITS
    èĨ
    0.07
    alion
    0.07
    ombo
    0.06
    ä½ĨéĢĻ
    0.06
    monto
    0.06
    /network
    0.06
    .prevent
    0.06
    tria
    0.06
    ležité
    0.06
    лада
    0.06
    Activations Density 0.009%

    No Known Activations