© 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. 22558
    Prev
    Next
    INDEX
    Explanations

    simple/basic concepts

    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
     domicile
    -0.06
    onge
    -0.06
    ç°¡åĸ®çļĦ
    -0.06
    æľĢ常çĶ¨çļĦ
    -0.06
    ueil
    -0.06
    对æĤ£èĢħ
    -0.06
    jord
    -0.06
    ongi
    -0.06
    enn
    -0.06
    ansa
    -0.06
    POSITIVE LOGITS
    严谨
    0.05
     ensuing
    0.05
    amt
    0.05
    uristic
    0.05
    gett
    0.05
    åĮ¡
    0.05
    å¦Ĥ
    0.05
     Heads
    0.05
    кÑĢо
    0.05
    ä¸įæĩĤ
    0.05
    Activations Density 0.012%

    No Known Activations