© 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. 20577
    Prev
    Next
    INDEX
    Explanations

    search database

    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
    çªį
    -0.06
    åīĬ
    -0.06
    ifest
    -0.06
    quir
    -0.05
    æ´¾
    -0.05
    пад
    -0.05
     Dani
    -0.05
    èĩªåĬĽ
    -0.05
    oltage
    -0.05
    èİ·å¾Ĺè¶ħè¿ĩ
    -0.05
    POSITIVE LOGITS
     restricted
    0.05
    ç©¿æ¢Ń
    0.05
    åı¹æģ¯
    0.05
    aksimalkan
    0.05
     ange
    0.05
     trapped
    0.05
     suites
    0.05
    èĬ³åįİ
    0.05
    usher
    0.05
    itations
    0.05
    Activations Density 0.046%

    No Known Activations