© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29776
    Prev
    Next
    INDEX
    Explanations

    recording and record events

    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
    çİĭåŃIJ
    -0.09
    èĨĿ
    -0.08
    é¾Ľ
    -0.08
    ãĤ¦ãĤ©
    -0.08
    æĬ½
    -0.08
    lamp
    -0.08
    inha
    -0.08
    åıªè§ģ
    -0.08
    æĬ½åıĸ
    -0.08
     theat
    -0.08
    POSITIVE LOGITS
    å½ķåĪ¶
    0.16
    å½ķ
    0.15
     recording
    0.13
    å½ķéŁ³
    0.11
    åīª
    0.11
    éĮĦ
    0.10
    æ£ļ
    0.10
     Recording
    0.10
     recordings
    0.10
    æįķæįī
    0.09
    Activations Density 0.121%

    No Known Activations