© 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. 18638
    Prev
    Next
    INDEX
    Explanations

    discriminatory, ethnic, or political terms

    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
    wan
    -0.06
    åĽŀ家
    -0.06
    adaran
    -0.06
    yno
    -0.06
    estens
    -0.06
    æĬ¥åĪ°
    -0.06
     amt
    -0.06
    ä»»ä½ķåªĴä½ĵ
    -0.06
    ноÑģÑĤи
    -0.05
    wick
    -0.05
    POSITIVE LOGITS
    ift
    0.05
    æľīåĬŁ
    0.05
     task
    0.05
    ilter
    0.05
     inequality
    0.05
    anf
    0.05
    ò
    0.05
     Task
    0.05
     alloc
    0.05
     ÑĢед
    0.05
    Activations Density 0.010%

    No Known Activations