© 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. 19992
    Prev
    Next
    INDEX
    Explanations

    bloom/blossom words

    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
    lexer
    -0.07
    opoly
    -0.06
    ë£Į를
    -0.06
    åŁºçĤ¹
    -0.06
    ibu
    -0.06
    ipu
    -0.06
    upun
    -0.06
    idual
    -0.06
    ieber
    -0.06
    éĿłæĭ¢
    -0.06
    POSITIVE LOGITS
    isses
    0.05
    çĿ
    0.05
    å½°
    0.05
    uate
    0.05
    رÙĩا
    0.05
    åĴĮæĮĩ导
    0.05
    çĭ
    0.05
     kỳ
    0.05
    à¸Ńà¸Ń
    0.05
    arnation
    0.05
    Activations Density 0.004%

    No Known Activations