© 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. 16764
    Prev
    Next
    INDEX
    Explanations

    projecting images or growth

    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
    presenta
    -0.07
    vole
    -0.06
    ifice
    -0.06
    åĦ¿çļĦ
    -0.06
    cle
    -0.06
    abouts
    -0.06
    ListOf
    -0.06
    tienen
    -0.05
    mehr
    -0.05
    fully
    -0.05
    POSITIVE LOGITS
    asper
    0.06
    rano
    0.06
     Broad
    0.06
    aimer
    0.06
    éné
    0.06
    ussi
    0.06
    iu
    0.06
    ién
    0.06
    ugu
    0.05
    รร
    0.05
    Activations Density 0.010%

    No Known Activations