© 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. 21265
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

    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
    ame
    -0.06
    ^{-
    -0.06
    ä¹ħ
    -0.06
    顺
    -0.06
    odied
    -0.05
     complex
    -0.05
    uca
    -0.05
    çij
    -0.05
    èĢĹ
    -0.05
    ^{
    -0.05
    POSITIVE LOGITS
    使åħ¶
    0.08
    αÏĤ
    0.07
    zan
    0.07
    estu
    0.06
    使å®ĥ
    0.06
    让åħ¶
    0.06
    使ä¹ĭ
    0.06
    æķ¢
    0.06
    让å®ĥ
    0.06
    ä¿Ŀè¯ģåħ¶
    0.06
    Activations Density 0.020%

    No Known Activations