© 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. 5238
    Prev
    Next
    INDEX
    Explanations

    and followed by list item

    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
    åį´æĺ¯
    -0.11
    åį´åıĪ
    -0.11
    å®Ŀå®ī
    -0.10
    ober
    -0.10
    磶
    -0.10
    æ·¡å®ļ
    -0.10
    åĿ
    -0.10
    OfWork
    -0.09
    åıįåĢĴ
    -0.09
    åį´
    -0.09
    POSITIVE LOGITS
    稷
    0.09
    gross
    0.09
    注æĦı
    0.08
     note
    0.08
     vice
    0.08
     nad
    0.08
    ÙĦÙī
    0.08
     dare
    0.08
     reve
    0.07
    åħ¶ä»ĸçļĦ
    0.07
    Activations Density 0.176%

    No Known Activations