© 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. 2021
    Prev
    Next
    INDEX
    Explanations

    Young (name, institution, term)

    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
    utow
    -0.09
     Lords
    -0.09
     lá»ĩ
    -0.09
    bout
    -0.09
    ients
    -0.09
    bage
    -0.09
    ting
    -0.09
    ä¼´
    -0.09
    cala
    -0.09
    æľŁéĻIJ
    -0.09
    POSITIVE LOGITS
    er
    0.11
    oot
    0.09
    owed
    0.09
    aroo
    0.09
    orman
    0.09
    峡谷
    0.09
     Homer
    0.08
     Conte
    0.08
    æ»´æ»´
    0.08
    飬
    0.08
    Activations Density 0.005%

    No Known Activations