© 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. 16854
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs

    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
    æľĢ大éĻIJ度
    -0.06
    ).-
    -0.06
     interd
    -0.06
    é¢ĨåħĪæ°´å¹³
    -0.05
    ial
    -0.05
    賦
    -0.05
    attra
    -0.05
    лÑĮкÑĥ
    -0.05
     Inclu
    -0.05
    pires
    -0.05
    POSITIVE LOGITS
     slowly
    0.06
    é¼ĵ
    0.06
    aja
    0.06
    unga
    0.06
    ode
    0.05
    aru
    0.05
    $$$
    0.05
     Hug
    0.05
    åħĪåIJİ
    0.05
    åĪĨ许
    0.05
    Activations Density 0.003%

    No Known Activations