© 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. 20340
    Prev
    Next
    INDEX
    Explanations

    word following "the"

    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
     identif
    -0.06
    æ°Ĺãģ«åħ¥ãĤĬãģ®
    -0.06
    andai
    -0.06
    inqu
    -0.06
    sworth
    -0.06
    ()][
    -0.06
     tind
    -0.06
     alá
    -0.05
    اÙĤرأ
    -0.05
     prescind
    -0.05
    POSITIVE LOGITS
    irs
    0.06
    é¬
    0.05
     set
    0.05
    çĶ
    0.05
    иÑĢо
    0.05
    عÙĦÙĬÙħ
    0.05
     satur
    0.05
     Flatten
    0.05
    å¤ļæķ¸
    0.05
    æĻĤãģ¾ãģ§
    0.05
    Activations Density 0.013%

    No Known Activations