© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21187
    Prev
    Next
    INDEX
    Explanations

    either option or condition

    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
    zier
    -0.06
    æĸĩåįİ
    -0.06
    å®Ĺ
    -0.06
    йÑĤ
    -0.06
    criptor
    -0.06
    к
    -0.06
    æķ´ä¸ªäºº
    -0.06
    å¤ļéĥ¨
    -0.06
    zt
    -0.05
    çļĦéģİç¨ĭä¸Ń
    -0.05
    POSITIVE LOGITS
    uzzi
    0.06
     caj
    0.05
    éĻħ
    0.05
    acol
    0.05
     cro
    0.05
     лей
    0.05
    以身
    0.05
    Ø·Ùħ
    0.05
    rew
    0.05
    æ¡ĥ
    0.05
    Activations Density 0.147%

    No Known Activations