© 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. 22386
    Prev
    Next
    INDEX
    Explanations

    technical terms and associated context

    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
     dire
    -0.05
     Dire
    -0.05
    æĭ¬
    -0.05
    axed
    -0.05
    /dir
    -0.05
     crap
    -0.05
     functionality
    -0.05
    å¾Ĺ天çĭ¬åİļçļĦ
    -0.05
    对äºİä¸ĢäºĽ
    -0.05
     alcance
    -0.05
    POSITIVE LOGITS
    istos
    0.06
    ิà¸Ķ
    0.06
    voie
    0.06
    ä¸Ģäºĭ
    0.06
    çļĦ主è§Ĥ
    0.06
    amakan
    0.06
    æĪIJç«ł
    0.06
    ouer
    0.06
    itia
    0.06
    ergus
    0.06
    Activations Density 0.149%

    No Known Activations