© 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. 30785
    Prev
    Next
    INDEX
    Explanations

    remembering and forgetting

    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
    çİ·
    -0.10
    ä¸ĢåĪĢ
    -0.09
    窥
    -0.09
    没æľīä»Ģä¹Ī
    -0.09
    _FLUSH
    -0.09
     Tear
    -0.08
    æĦıè§ģåıįé¦Ī
    -0.08
    æĹłä¸į
    -0.08
    æ¯ĶæĪij
    -0.08
    ensed
    -0.08
    POSITIVE LOGITS
    å¿ĺè®°
    0.17
    å¿ĺ
    0.15
    å¿ĺäºĨ
    0.14
     forget
    0.14
    å¿ĺè®°äºĨ
    0.14
    éģĹå¿ĺ
    0.14
     forgetting
    0.12
    æ¼ı
    0.12
    å¿ĺãĤĮ
    0.12
     quên
    0.11
    Activations Density 0.083%

    No Known Activations