© 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. 19767
    Prev
    Next
    INDEX
    Explanations

    Evil Games angela marsons

    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
    au
    -0.05
     Thorn
    -0.05
     cod
    -0.05
     narr
    -0.05
    Ñģк
    -0.05
    aced
    -0.05
    oe
    -0.05
    ظاÙħ
    -0.05
     saja
    -0.05
    è¿Ļ两
    -0.05
    POSITIVE LOGITS
    inci
    0.06
    æĬĬ人
    0.06
    没æľīåľ¨
    0.06
    å¯¹æľ¬
    0.06
    ært
    0.05
    è°ģçŁ¥éģĵ
    0.05
    æľīäººåľ¨
    0.05
    רק
    0.05
    æĹłåı¯
    0.05
    opter
    0.05
    Activations Density 0.001%

    No Known Activations