© 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. 47410
    Prev
    Next
    INDEX
    Explanations

    benefits and advantages

    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
    æ¶ī
    -0.10
    ault
    -0.10
    IENT
    -0.09
    ç»ĩ
    -0.09
    CHIP
    -0.08
    (Core
    -0.08
    åİĨåı²æĢ§
    -0.08
    iez
    -0.08
    utions
    -0.08
    tesy
    -0.08
    POSITIVE LOGITS
    çļĦ好å¤Ħ
    0.13
    çļĦéĩįè¦ģæĢ§
    0.12
     пÑĢеимÑĥÑīеÑģÑĤв
    0.11
    ä¼ĺåĬ¿
    0.11
    好å¤Ħ
    0.10
     importance
    0.10
     Importance
    0.10
     Benefits
    0.10
    çļĦä¼ĺåĬ¿
    0.10
     benefits
    0.10
    Activations Density 0.102%

    No Known Activations