© 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. 63988
    Prev
    Next
    INDEX
    Explanations

    unless, gone, except

    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
    Negative Logits
    çİĭèĢħ
    -0.10
    ä¼ļéķ¿
    -0.10
    罡
    -0.09
    è¿İ
    -0.09
    å¤ļéĩį
    -0.09
    åĢĻ
    -0.09
    anni
    -0.09
    onet
    -0.09
    chio
    -0.09
    ç³»
    -0.09
    POSITIVE LOGITS
    éĻ¤éĿŀ
    0.11
    åĵªæĢķæĺ¯
    0.09
     Except
    0.09
    鼳
    0.08
    except
    0.08
    èĥģ
    0.08
     Gone
    0.08
     trừ
    0.08
    åıªè§ģ
    0.08
     unless
    0.08
    Activations Density 0.014%

    No Known Activations