© 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. 16816
    Prev
    Next
    INDEX
    Explanations

    "to" + verb

    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
    éĩı
    -0.07
     phép
    -0.06
    é¡
    -0.06
    ä¸ĵäººè´Łè´£
    -0.06
    大èĥĨçļĦ
    -0.06
    arding
    -0.06
    емÑĭ
    -0.06
    ’d
    -0.06
    ãĤĤãĤī
    -0.06
    blank
    -0.05
    POSITIVE LOGITS
    æĬī
    0.05
     usufruire
    0.05
    avax
    0.05
    stig
    0.05
    åºĶè¯ī
    0.05
    faz
    0.05
    icca
    0.05
    stÄĻp
    0.05
    æĸ°åĬłåĿ¡
    0.05
    èħ»
    0.05
    Activations Density 0.007%

    No Known Activations