© 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. 12388
    Prev
    Next
    INDEX
    Explanations

    memes

    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
     Huss
    -0.08
    æī¹
    -0.08
    ROSS
    -0.08
    newInstance
    -0.08
    oen
    -0.08
     prag
    -0.08
    ross
    -0.08
    омеÑĢ
    -0.07
    umped
    -0.07
    沦
    -0.07
    POSITIVE LOGITS
    åĦ¿
    0.10
     ÐĴлад
    0.10
     Osw
    0.09
    BOARD
    0.09
    vironment
    0.09
    大åħ¨
    0.09
    Ñģк
    0.09
    轿
    0.09
    è·Ľ
    0.09
    erals
    0.09
    Activations Density 0.009%

    No Known Activations