© 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. 9225
    Prev
    Next
    INDEX
    Explanations

    restore and restoration

    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
    igel
    -0.09
    odiac
    -0.09
    ยà¸Ńม
    -0.09
    温
    -0.09
    åĢ¼å®Ī
    -0.08
    ulos
    -0.08
    åħ¥ãĤĬ
    -0.08
     Anast
    -0.08
    çķı
    -0.08
     fool
    -0.08
    POSITIVE LOGITS
     restoration
    0.13
    æģ¢å¤į
    0.12
    ä¹¾åĿ¤
    0.12
    æģ¢å¤įæŃ£å¸¸
    0.12
     restoring
    0.11
     restored
    0.11
    çİ°çĬ¶
    0.11
     restore
    0.11
     Restoration
    0.11
     Restore
    0.10
    Activations Density 0.074%

    No Known Activations