© 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. 18948
    Prev
    Next
    INDEX
    Explanations

    medical and societal issues

    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
    ç»ħ
    -0.05
    ake
    -0.05
     U
    -0.05
    hatikan
    -0.04
     spec
    -0.04
    imes
    -0.04
     ÑĤ
    -0.04
     ext
    -0.04
    <think>
    -0.04
    Į
    -0.04
    POSITIVE LOGITS
    æŃ»
    0.08
    adero
    0.06
     vano
    0.06
    ÑĢек
    0.06
    unted
    0.06
    rush
    0.06
    ؤÙĩا
    0.06
    achs
    0.06
    ä¼Łå¤§å¤įåħ´
    0.06
    åĴĮçĪ±
    0.05
    Activations Density 0.021%

    No Known Activations