© 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. 20042
    Prev
    Next
    INDEX
    Explanations

    people and places

    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
    å°ı家
    -0.06
    åĿļåĽº
    -0.06
    éħ¬
    -0.06
    ìĪł
    -0.06
    atr
    -0.06
    ä¼ļæīĢ
    -0.06
    次è¦ģ
    -0.06
    çľģæŶ
    -0.06
     nanti
    -0.06
    表éĿ¢
    -0.05
    POSITIVE LOGITS
     simply
    0.05
     Simply
    0.05
     ke
    0.05
    keit
    0.05
    lež
    0.05
    åIJijè®°èĢħ
    0.05
    ucer
    0.05
    ITOS
    0.05
    van
    0.05
     jointly
    0.05
    Activations Density 0.687%

    No Known Activations