© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17236
    Prev
    Next
    INDEX
    Explanations

    under section or chapter

    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
     sosta
    -0.06
    ânia
    -0.06
    urt
    -0.06
    ãĥ¼ãĤ·ãĥ§ãĥ³
    -0.05
    aktu
    -0.05
    رضا
    -0.05
    URT
    -0.05
     ube
    -0.05
    exe
    -0.05
    /she
    -0.05
    POSITIVE LOGITS
    èĩªæĪIJç«ĭ以æĿ¥
    0.06
    ä¸į失
    0.06
    管çIJĨæ³ķ
    0.06
    以æĿ¥
    0.06
    ست
    0.06
    agian
    0.05
    ngle
    0.05
     Ñģка
    0.05
    ÙĪÙĬÙĦ
    0.05
    ä¸įä¹ħçļĦ
    0.05
    Activations Density 0.033%

    No Known Activations