© 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. 20484
    Prev
    Next
    INDEX
    Explanations

    content between braces

    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
    aise
    -0.06
    è¡£æľįçļĦ
    -0.06
    æħİ
    -0.06
    å½Ĵæł¹
    -0.06
    Socket
    -0.05
    aises
    -0.05
    ä¿ĥ使
    -0.05
    ä¸įåIJĪ
    -0.05
    urry
    -0.05
    Sock
    -0.05
    POSITIVE LOGITS
     vzd
    0.06
    dar
    0.06
    ×Ĺ
    0.05
    dam
    0.05
    OSP
    0.05
    å·»ãģį
    0.05
     Includes
    0.05
     darunter
    0.05
    åĬĽä½ľ
    0.05
    works
    0.05
    Activations Density 0.046%

    No Known Activations