© 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. 19783
    Prev
    Next
    INDEX
    Explanations

    well drained

    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
    å°Ŀ
    -0.05
    æ°Ľ
    -0.05
    ä¸Ģ转
    -0.05
     “
    -0.05
     hon
    -0.05
    Å¡Ä·
    -0.05
    wer
    -0.05
    ott
    -0.05
    ç»´æĬ¤
    -0.05
    imen
    -0.05
    POSITIVE LOGITS
    Ñģловно
    0.06
    nergy
    0.06
    rael
    0.06
    ÙĪدÙĬØ©
    0.06
    ness
    0.06
    ÑĢÑĭн
    0.06
    phin
    0.06
    çļĦæľĭåıĭåı¯ä»¥
    0.06
    acts
    0.05
    nergie
    0.05
    Activations Density 0.001%

    No Known Activations