© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16685
    Prev
    Next
    INDEX
    Explanations

    remember followed by what

    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
    Negative Logits
    ues
    -0.06
    çĦ¶æĺ¯
    -0.06
    an
    -0.06
    iem
    -0.06
    ever
    -0.06
    raries
    -0.06
    ivid
    -0.05
    ecchio
    -0.05
    اÙĭ
    -0.05
     memory
    -0.05
    POSITIVE LOGITS
    ors
    0.06
    ÛĮÙĨÙĩ
    0.06
    orate
    0.06
    mier
    0.06
    å¦ĥ
    0.06
    olean
    0.06
    íĽ¨
    0.06
    ÑĢегÑĥли
    0.06
     auk
    0.06
    oir
    0.05
    Activations Density 0.006%

    No Known Activations