© 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. 18533
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åħ¼
    -0.05
    åĴĮéĥ¨åĪĨ
    -0.05
    å°Ķ
    -0.05
    éĢIJä¸Ģ
    -0.05
    èµĭ
    -0.05
    win
    -0.05
    ä¹ħä¹ĭ
    -0.05
     chéo
    -0.05
    uish
    -0.05
    terminal
    -0.05
    POSITIVE LOGITS
    angles
    0.06
    ients
    0.06
    尼西äºļ
    0.06
    oric
    0.06
    å½±
    0.06
    Angles
    0.06
     Reign
    0.06
    :size
    0.06
    æģ¯
    0.06
    ovac
    0.05
    Activations Density 0.000%

    No Known Activations