© 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. 64061
    Prev
    Next
    INDEX
    Explanations

    delight yourguarantee youplenty of promotionsfun noteglimpse of thebecome a scuba divertalking and creatingwill also find

    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
    .fm
    -0.10
    ãĤµãĥ¼
    -0.09
    骨æŀ¶
    -0.09
    çijŁ
    -0.08
    åıijè¨Ģ
    -0.08
    骨
    -0.08
    éĢĨ
    -0.08
    Fa
    -0.08
    å®ļçĤ¹
    -0.08
    寸
    -0.08
    POSITIVE LOGITS
    ä¸Ģ件äºĭ
    0.10
    æ·ĭ
    0.10
    裹
    0.09
    ä¹ĭæĹħ
    0.09
    为大家
    0.09
    为æĤ¨
    0.09
    ipeg
    0.09
    å®Įç¾İ
    0.09
    ponsive
    0.08
    åIJ¬åIJ¬
    0.08
    Activations Density 0.237%

    No Known Activations