© 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. 26312
    Prev
    Next
    INDEX
    Explanations

    K in names or specific terms

    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
    esign
    -0.09
    åī¯
    -0.09
    èĭį
    -0.09
    å¤ļåįĬ
    -0.08
    unc
    -0.08
    åĮĻ
    -0.08
    室åıĭ
    -0.08
    涣
    -0.08
    è¨Ģè¯Ń
    -0.08
    ennis
    -0.08
    POSITIVE LOGITS
    æ´¸
    0.10
    ocking
    0.10
    iating
    0.09
    åİĨå¹´
    0.09
    蹦
    0.09
    ometer
    0.09
    æĵĴ
    0.08
    æŁĵ
    0.08
     cons
    0.08
     недо
    0.08
    Activations Density 0.089%

    No Known Activations