© 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. 21719
    Prev
    Next
    INDEX
    Explanations

    listing things after "and"

    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
     thus
    -0.06
    Ùĭا
    -0.06
    ä½ľåĪĻ
    -0.06
     بذÙĦÙĥ
    -0.05
    бÑĥдÑĮ
    -0.05
     inilah
    -0.05
    ãģ¾ãģĹãģ¦
    -0.05
    ä»Ģä¹Īæĺ¯
    -0.05
    érc
    -0.05
    æį¢è¨Ģä¹ĭ
    -0.05
    POSITIVE LOGITS
    å¤ļæĸ¹éĿ¢çļĦ
    0.06
    moil
    0.06
    fé
    0.06
     entirety
    0.06
    fade
    0.06
    åĩºå¸ŃäºĨ
    0.06
    omba
    0.05
    åĮ»èį¯åį«çĶŁ
    0.05
    ç§ijåѦä¸İå·¥ç¨ĭ
    0.05
    tap
    0.05
    Activations Density 0.016%

    No Known Activations