© 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. 20558
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
    ness
    -0.07
    pper
    -0.07
    è¯ĿæĿ¥
    -0.07
    pling
    -0.06
    heid
    -0.06
    cake
    -0.06
    nable
    -0.06
    бÑĥдÑĮÑĤе
    -0.06
    ¾
    -0.06
    mittel
    -0.06
    POSITIVE LOGITS
    ancock
    0.09
    اث
    0.06
    pike
    0.06
    çĦ¶æĺ¯
    0.06
    об
    0.06
    bart
    0.06
    vement
    0.06
    krieg
    0.06
    esta
    0.06
    çĦ¶å¤§
    0.06
    Activations Density 0.217%

    No Known Activations