© 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. 18621
    Prev
    Next
    INDEX
    Explanations

    results

    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
    anko
    -0.06
    ansch
    -0.06
    ingham
    -0.06
    ä¸ĩåıĺ
    -0.05
    åIJĮæ¯Ķä¸ĭéĻį
    -0.05
    å¾·æīį
    -0.05
    åĬłåħ¥ä¸ŃåĽ½åħ±äº§åħļ
    -0.05
    rens
    -0.05
    çŃīèµĦæĸĻ
    -0.05
     amendments
    -0.05
    POSITIVE LOGITS
     previous
    0.10
    previous
    0.09
    Previous
    0.09
     Previous
    0.09
     пÑĢедÑĭ
    0.08
    _prev
    0.08
    ä¸Ĭä¸Ģ
    0.08
     earlier
    0.08
    ä¹ĭåīįçļĦ
    0.08
    _previous
    0.07
    Activations Density 0.272%

    No Known Activations