© 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. 19130
    Prev
    Next
    INDEX
    Explanations

    no / non / free / not

    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
    δικ
    -0.06
    (er
    -0.05
    ÄĻ
    -0.05
    ä¹Łæľīä¸Ģå®ļçļĦ
    -0.05
    çĶŁåij½åĢ¼
    -0.05
    çijķ
    -0.05
    对åIJĦç§į
    -0.05
    ãģŁãģ³
    -0.05
     im
    -0.05
     const
    -0.05
    POSITIVE LOGITS
    å¾ĵ
    0.07
     notorious
    0.06
    ä¹Łä¸į
    0.06
    lice
    0.06
    ä¼łç»Ł
    0.06
    traditional
    0.06
    kola
    0.05
     chamb
    0.05
    åĬ©
    0.05
     наÑģÑĤоÑı
    0.05
    Activations Density 0.061%

    No Known Activations