© 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. 3030
    Prev
    Next
    INDEX
    Explanations

    merge, segue, meld

    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
    loff
    -0.10
    antas
    -0.09
     Wings
    -0.09
    afia
    -0.09
    verbs
    -0.09
    éĻIJãĤĬ
    -0.08
    ecast
    -0.08
    аÑģÑĤ
    -0.08
     Со
    -0.08
    suppress
    -0.08
    POSITIVE LOGITS
    æľŁåĨħ
    0.10
    åľ¨ä¸Ģèµ·
    0.09
     into
    0.09
    涧
    0.09
    Into
    0.09
    çĬĢ
    0.08
    妾
    0.08
     acos
    0.08
    into
    0.08
    è¿ijä¹İ
    0.08
    Activations Density 0.012%

    No Known Activations