© 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. 20527
    Prev
    Next
    INDEX
    Explanations

    data structures: queue, stack, first-order

    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
    éĴĪ对
    -0.06
    ãģŁãģŁ
    -0.06
    entes
    -0.05
    éĴĪ对æĢ§
    -0.05
    >+
    -0.05
    itrine
    -0.05
    angkit
    -0.05
    ä¹Įéķĩ
    -0.05
    å¾ģ
    -0.05
    çīĪåĽ¾
    -0.05
    POSITIVE LOGITS
    hoa
    0.06
    olla
    0.06
    çħĮ
    0.05
    ìĿµ
    0.05
    nger
    0.05
     '`
    0.05
    ç»ĵ
    0.05
    spot
    0.05
     annivers
    0.05
     Columb
    0.05
    Activations Density 0.002%

    No Known Activations