© 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. 18665
    Prev
    Next
    INDEX
    Explanations

    coding=utf-8 or encoding

    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
    ation
    -0.05
    Âł
    -0.05
    ·
    -0.05
    ov
    -0.05
    thesis
    -0.05
    APS
    -0.05
    দà§ĩর
    -0.05
    ous
    -0.05
    rang
    -0.05
    e
    -0.04
    POSITIVE LOGITS
    {o
    0.07
    emblée
    0.06
    èĴĻå¾·
    0.06
    wiss
    0.06
    äºĨä¸ĢæĿ¡
    0.06
    æĸ¹æ³ķè¿Ľè¡Į
    0.06
    æĸ°åĬłåĿ¡
    0.06
    StringLength
    0.06
    utam
    0.06
    cidental
    0.06
    Activations Density 0.001%

    No Known Activations