© 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. 12306
    Prev
    Next
    INDEX
    Explanations

    lug, luge, lugo, luffa

    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
    виÑĤ
    -0.11
    ä¿Ł
    -0.10
    assen
    -0.10
    èĢģåŃIJ
    -0.09
    çĥŁåĽ±
    -0.09
    åĮºåĨħ
    -0.09
    OVE
    -0.09
    åĮºç®¡å§Ķä¼ļ
    -0.09
    ynos
    -0.08
    idget
    -0.08
    POSITIVE LOGITS
    auge
    0.11
    ä¹İ
    0.09
    town
    0.09
    ingly
    0.08
    lr
    0.08
    anking
    0.08
    anked
    0.08
    mouth
    0.08
    ester
    0.08
    ional
    0.08
    Activations Density 0.001%

    No Known Activations