© 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. 19079
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ä¹ĭæĢ¥
    -0.06
    ucid
    -0.06
    çµŀ
    -0.06
    ideo
    -0.06
    ihn
    -0.06
    çºł
    -0.06
     заÑĤо
    -0.06
    quest
    -0.06
    amic
    -0.06
    ille
    -0.06
    POSITIVE LOGITS
    çĶŁ
    0.07
    éĻĮçĶŁ
    0.06
    èĤļ
    0.06
    æķ£è£ħ
    0.06
    éĢĤ度çļĦ
    0.06
    Ups
    0.06
     AIS
    0.06
    大ä¸įäºĨ
    0.06
    鸦
    0.05
    ä¸īå¹´çļĦ
    0.05
    Activations Density 0.005%

    No Known Activations