© 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. 21534
    Prev
    Next
    INDEX
    Explanations

    correct image, units digit, prime factors, numbers

    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
    æŃ£å¼ı
    -0.06
    är
    -0.05
    verz
    -0.05
    å
    -0.05
    åŃĹ
    -0.05
    åħ¨æ°ij
    -0.05
    gren
    -0.05
    illi
    -0.05
    度
    -0.05
    ä¸ĩ
    -0.05
    POSITIVE LOGITS
    Ñħни
    0.06
    à¹Ģศ
    0.06
    TestMethod
    0.06
     strut
    0.06
    rompt
    0.06
    chter
    0.06
    anken
    0.06
     Borgo
    0.05
    çĭ¬ç«ĭçļĦ
    0.05
    kob
    0.05
    Activations Density 0.001%

    No Known Activations