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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20982
    Prev
    Next
    INDEX
    Explanations

    cream or creams

    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
     pháºŃn
    -0.10
    imes
    -0.09
     ÑĢÑıд
    -0.09
    reck
    -0.09
    à¹Ħà¸ģล
    -0.09
    gers
    -0.08
    urnal
    -0.08
    itives
    -0.08
    à¹Ģà¸īà¸ŀาะ
    -0.08
    urn
    -0.08
    POSITIVE LOGITS
    ie
    0.11
    lining
    0.10
    ier
    0.10
    ajor
    0.10
    ../../../
    0.10
    iest
    0.09
    iqu
    0.09
    er
    0.09
    ming
    0.09
    èĬĿ
    0.09
    Activations Density 0.004%

    No Known Activations