© 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. 18639
    Prev
    Next
    INDEX
    Explanations

    latest news, report, episode, effort

    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
    สà¸ĩ
    -0.06
    werp
    -0.06
     everywhere
    -0.06
    thinkable
    -0.06
    ÙĤر
    -0.06
    绽
    -0.06
    ston
    -0.06
    ä¸Ģæł·çļĦ
    -0.06
    Jul
    -0.05
    该款
    -0.05
    POSITIVE LOGITS
    ç¨ĭ度çļĦ
    0.06
    chief
    0.05
    ileo
    0.05
    بغÙĬ
    0.05
    ugen
    0.05
     greatness
    0.05
    ëģĶ
    0.05
    indelijk
    0.05
    olate
    0.05
    äºĨçīĩåĪ»
    0.05
    Activations Density 0.011%

    No Known Activations