© 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. 18535
    Prev
    Next
    INDEX
    Explanations

    programming nouns after articles

    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
     miliard
    -0.05
    vlo
    -0.05
    èĴĻå¾·
    -0.05
     pokoj
    -0.05
    è¿Ļæĺ¯
    -0.05
    Äħpi
    -0.05
    bol
    -0.05
    æ°´å¹³çļĦ
    -0.05
    ersh
    -0.05
    å°Ĩ
    -0.05
    POSITIVE LOGITS
    gether
    0.08
    oir
    0.07
    à¹Īà¸Ļัà¹īà¸Ļ
    0.05
    igna
    0.05
    æĺİå¹´çļĦ
    0.05
    êµ´
    0.05
    ÑĩеÑĤе
    0.05
    ix
    0.05
    idget
    0.05
    igne
    0.05
    Activations Density 0.029%

    No Known Activations