© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21924
    Prev
    Next
    INDEX
    Explanations

    butter and related ingredients

    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
    lander
    -0.05
    оÑģÑĤÑĮ
    -0.05
    ç³»
    -0.05
    пан
    -0.05
    attan
    -0.05
    pod
    -0.05
    qq
    -0.05
    é¢
    -0.05
    èħ¹
    -0.05
    人
    -0.05
    POSITIVE LOGITS
    ÑĢаÑĩи
    0.07
    enca
    0.06
    cream
    0.06
    ÑģкÑĢÑĭ
    0.06
    orra
    0.06
    plug
    0.06
    åĽ¢æĪIJåijĺ
    0.06
    coes
    0.06
    ÑĪки
    0.06
    arre
    0.06
    Activations Density 0.004%

    No Known Activations