© 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. 18811
    Prev
    Next
    INDEX
    Explanations

    units and concentrations

    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
    egah
    -0.07
    iÄĻ
    -0.07
    ojis
    -0.06
    egn
    -0.06
    nder
    -0.06
    ello
    -0.06
    ราว
    -0.06
    untut
    -0.06
    andangan
    -0.06
     DÃŃky
    -0.06
    POSITIVE LOGITS
    ä¸į离
    0.06
    éken
    0.05
    hafte
    0.05
    æľºä¸Ĭ
    0.05
    éĩĮ头
    0.05
    -filled
    0.05
    -rich
    0.05
    лиÑĨа
    0.05
     holistic
    0.04
    æľĢåIJİè¿ĺæĺ¯
    0.04
    Activations Density 0.037%

    No Known Activations