© 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. 19777
    Prev
    Next
    INDEX
    Explanations

    wealthy or rich followed by descriptive nouns

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.06
    uft
    -0.06
    伸æīĭ
    -0.06
    ignes
    -0.06
    ÙĪÙħØ©
    -0.06
    à¸Ľà¸IJม
    -0.06
    lant
    -0.06
    ukka
    -0.06
    转ä¸ļ
    -0.05
     trad
    -0.05
    POSITIVE LOGITS
    iao
    0.06
    iver
    0.05
     Infatti
    0.05
    æĢİä¹ĪäºĨ
    0.05
     matchups
    0.05
    å½ĵä¹ĭ
    0.05
    认为æĺ¯
    0.05
    -su
    0.05
     intrigued
    0.05
    vrier
    0.05
    Activations Density 0.007%

    No Known Activations