© 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. 18897
    Prev
    Next
    INDEX
    Explanations

    resulting

    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
    ly
    -0.05
    bed
    -0.05
    inton
    -0.05
    ble
    -0.05
     pers
    -0.05
    ä¹°çĤ¹
    -0.05
    ming
    -0.05
    ؤÙĦ
    -0.05
    侯
    -0.05
    consider
    -0.05
    POSITIVE LOGITS
    ãģĦãģŁãģ®ãģ§
    0.07
    lections
    0.07
    å¤ļå¹´ä¾Ĩ
    0.07
    ÑĢÑı
    0.07
    ä¸ĢäºĮ
    0.06
    ÐĿЯ
    0.06
    maal
    0.06
     Agreg
    0.06
    sze
    0.06
    ory
    0.06
    Activations Density 0.003%

    No Known Activations