© 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. 20382
    Prev
    Next
    INDEX
    Explanations

    clicking on interface elements

    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
    pars
    -0.07
    èĬ±å¼Ģ
    -0.06
    ustum
    -0.06
    оÑĢÑĥ
    -0.06
    pong
    -0.06
    èĤĨ
    -0.06
    å¥ķ
    -0.06
    startup
    -0.06
    æĢĴäºĨ
    -0.06
    ưỡng
    -0.06
    POSITIVE LOGITS
    0.06
     major
    0.05
     vol
    0.05
     pack
    0.05
    iset
    0.05
     adjoining
    0.05
     neoliber
    0.05
    彬
    0.05
     cool
    0.05
     assorted
    0.05
    Activations Density 0.003%

    No Known Activations