© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 39516
    Prev
    Next
    INDEX
    Explanations

    but followed by articles or adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    .Reader
    -0.09
    cono
    -0.09
    ça
    -0.09
    nen
    -0.09
    åĩĽ
    -0.09
    clus
    -0.09
     ì²ĺ
    -0.08
    ãģĨãģ¡
    -0.08
     Girlfriend
    -0.08
     cabin
    -0.08
    POSITIVE LOGITS
    ters
    0.12
    寥
    0.10
    ties
    0.09
    owski
    0.09
    iful
    0.09
    åĩłåįĥ
    0.09
    ted
    0.08
    tes
    0.08
    åĪĨ解
    0.08
    ãĤ¥
    0.08
    Activations Density 0.049%

    No Known Activations