© 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. 16682
    Prev
    Next
    INDEX
    Explanations

    honored to be

    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
    åĨ·åĨ·
    -0.09
    é²ľæ´»
    -0.09
    enet
    -0.09
    æķ´é¡¿
    -0.09
    åħ¸åŀĭ
    -0.09
    åīįéĶĭ
    -0.08
    azzi
    -0.08
    妹åŃIJ
    -0.08
    èŀįåIJĪåıijå±ķ
    -0.08
    æİ·
    -0.08
    POSITIVE LOGITS
    éĻ¶
    0.10
    ulas
    0.10
    engan
    0.09
     ghé
    0.09
    -Jan
    0.09
    ë¹µ
    0.09
    inaire
    0.09
    èĨº
    0.09
    stras
    0.08
    .activation
    0.08
    Activations Density 0.004%

    No Known Activations