© 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. 20872
    Prev
    Next
    INDEX
    Explanations

    know

    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
    kü
    -0.05
    å³¥åµĺ
    -0.05
     difference
    -0.05
    è¦ģç»Ļ
    -0.05
    wort
    -0.05
    ัà¸ĩ
    -0.05
    YES
    -0.05
    quir
    -0.05
    æ¯Ķ
    -0.05
    itch
    -0.04
    POSITIVE LOGITS
    autant
    0.07
    ä¸ĩ次
    0.07
    Ñĭ
    0.06
    INESS
    0.06
     nächste
    0.06
    iments
    0.06
    ings
    0.06
    樣çļĦ
    0.06
     ide
    0.06
    ukka
    0.06
    Activations Density 0.007%

    No Known Activations