© 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. 18573
    Prev
    Next
    INDEX
    Explanations

    according to dates and times

    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
    MATCH
    -0.06
    YPE
    -0.06
    ãģįãĤĥ
    -0.05
    MAL
    -0.05
     bronze
    -0.05
    uder
    -0.05
    äude
    -0.05
    bat
    -0.05
    axy
    -0.05
    rieben
    -0.05
    POSITIVE LOGITS
    æ¡¥
    0.07
    ossa
    0.06
    &T
    0.05
    ãĥµ
    0.05
    æ¯ı次
    0.05
     rek
    0.05
    رج
    0.05
    éŀ
    0.05
    äºĭ
    0.05
    ong
    0.05
    Activations Density 0.001%

    No Known Activations