© 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. 22003
    Prev
    Next
    INDEX
    Explanations

    had/have/’ve + past participle/noun

    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
    outh
    -0.06
     supr
    -0.06
     sn
    -0.05
    sn
    -0.05
    rew
    -0.05
     recons
    -0.05
    æ¶
    -0.05
     gio
    -0.05
     vali
    -0.05
    rang
    -0.05
    POSITIVE LOGITS
    alde
    0.06
    าà¸Ķ
    0.06
     tolle
    0.06
    ç¾¤å²Ľ
    0.06
    人åĿĩåı¯
    0.06
    æĦıæĥ³
    0.06
    alda
    0.06
     rádi
    0.06
    并æİ¥åıĹ
    0.06
    bedo
    0.06
    Activations Density 0.002%

    No Known Activations