© 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. 31002
    Prev
    Next
    INDEX
    Explanations

    Aaron followed by a surname

    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
    åīįæīĢ
    -0.11
    amp
    -0.09
    heets
    -0.09
    ë¡Ŀ
    -0.09
    оÑĤ
    -0.09
    Ļ
    -0.08
    ëį°
    -0.08
    eki
    -0.08
    絾
    -0.08
    Ĭ
    -0.08
    POSITIVE LOGITS
    naire
    0.12
    alis
    0.11
    naires
    0.10
    alysis
    0.10
    ution
    0.10
    acha
    0.10
    ãģĦãĤĭ
    0.10
    amento
    0.09
    ãģ¹ãģį
    0.09
    ials
    0.09
    Activations Density 0.020%

    No Known Activations