© 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. 20691
    Prev
    Next
    INDEX
    Explanations

    list item number or configuration

    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
    onda
    -0.06
     pros
    -0.06
    ç¿»äºĨ
    -0.06
    éĶ¡
    -0.06
    éĢ¢
    -0.06
    ãĤ¸ãĥ³ãĤ°
    -0.05
    åĨĻçļĦ
    -0.05
    γÏĮ
    -0.05
    uta
    -0.05
    nungs
    -0.05
    POSITIVE LOGITS
    ink
    0.06
    jeti
    0.06
    æľªçĦ¶
    0.06
    ities
    0.05
    ités
    0.05
    ↵↵
    0.05
    exe
    0.05
    alama
    0.05
    ä¸įæĺ¯å¾Ī好
    0.05
    æĢĿæĥ³åĴĮè¡ĮåĬ¨
    0.05
    Activations Density 0.060%

    No Known Activations