© 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. 18613
    Prev
    Next
    INDEX
    Explanations

    play and games

    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
    ation
    -0.09
    Ø©
    -0.07
    ATION
    -0.07
    ing
    -0.06
    ting
    -0.06
    èī¯å¥½çļĦ
    -0.06
    ÏĤ
    -0.06
    ï¸ı
    -0.05
     whatever
    -0.05
    icient
    -0.05
    POSITIVE LOGITS
    ures
    0.07
    หยุà¹Īà¸Ļ
    0.06
     maxx
    0.06
    注æĦıçļĦæĺ¯
    0.06
    Ñģловно
    0.06
    Ñĩай
    0.06
    Ñĥк
    0.06
    ÅĤad
    0.06
     Powerful
    0.06
     Pandemi
    0.06
    Activations Density 0.008%

    No Known Activations