© 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. 19221
    Prev
    Next
    INDEX
    Explanations

    locations and entities

    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
    æľĽ
    -0.06
     o
    -0.05
     complete
    -0.05
    渤
    -0.05
    ä¸įåIJĮ
    -0.05
    è¦ģèµ°
    -0.05
    rine
    -0.05
    ä
    -0.05
    çļĦä¸Ĭ
    -0.05
    issimo
    -0.05
    POSITIVE LOGITS
    nicz
    0.07
    agua
    0.07
     Nothing
    0.06
    nich
    0.06
     nothing
    0.06
    isto
    0.06
    -normal
    0.06
    orno
    0.06
     íĬ¹ë³Ħíķľ
    0.06
    çī¹åĪ¥
    0.06
    Activations Density 0.029%

    No Known Activations