© 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. 18979
    Prev
    Next
    INDEX
    Explanations

    names of people and organizations

    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
    ä¸İä¹ĭ
    -0.06
    &E
    -0.06
    åĪĨåĪ«ä¸İ
    -0.06
    ä¸İ
    -0.06
    ìĻĢìĿĺ
    -0.06
    ãģ¨ãģ®
    -0.05
    arris
    -0.05
    èĪĩ
    -0.05
     mistr
    -0.05
    人ä¸İ
    -0.05
    POSITIVE LOGITS
    ffet
    0.06
    åĽłç´łå½±åĵį
    0.05
    èĢģå¸Ī说
    0.05
    对æĪijåĽ½
    0.05
    :num
    0.05
    ouvrez
    0.05
    ulling
    0.05
    quer
    0.05
    eer
    0.05
    è´Łæľī
    0.05
    Activations Density 0.021%

    No Known Activations