© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20236
    Prev
    Next
    INDEX
    Explanations

    past, recent years

    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
    çĥĽ
    -0.12
     вÑĭÑģоко
    -0.10
    ä¸Ģ个éĹ®é¢ĺ
    -0.10
    åįİ缼
    -0.09
    说å®Į
    -0.09
    河边
    -0.09
    åģľä¸ĭ
    -0.09
    ãģĿãĤĮãģ§ãĤĤ
    -0.08
    èº²åľ¨
    -0.08
    çĸ¼
    -0.08
    POSITIVE LOGITS
    以æĿ¥
    0.10
    è¿Ļåĩłå¹´
    0.10
    ä»ĬåIJİ
    0.10
    acos
    0.10
     past
    0.09
     recent
    0.09
    åĩĨåĪĻ
    0.09
    ettel
    0.09
    past
    0.09
    è¿ijæľŁ
    0.09
    Activations Density 0.152%

    No Known Activations