© 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. 18517
    Prev
    Next
    INDEX
    Explanations

    video signal country document popup

    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
     اÙĦÙħج
    -0.07
    æīĢæľīæĿĥ
    -0.06
    æ£ĢæŁ¥ä¸Ģä¸ĭ
    -0.06
     Ùħج
    -0.06
    imir
    -0.06
     dint
    -0.06
    менÑĥ
    -0.06
    familien
    -0.05
    caf
    -0.05
    "h
    -0.05
    POSITIVE LOGITS
    çļĦè¿ĺæĺ¯
    0.06
     Bed
    0.05
     kurs
    0.05
    çªģ
    0.05
     prior
    0.05
    å·²åıĸå¾Ĺ
    0.05
    ap
    0.05
    prior
    0.05
    奪
    0.05
     topping
    0.05
    Activations Density 0.066%

    No Known Activations