© 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. 12266
    Prev
    Next
    INDEX
    Explanations

    chance to

    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
    sson
    -0.12
    ends
    -0.10
    uxe
    -0.10
    ding
    -0.10
     обÑıзан
    -0.09
    ocity
    -0.09
     Gallagher
    -0.09
    nt
    -0.09
    à¹Į
    -0.09
    èĪ«
    -0.09
    POSITIVE LOGITS
    lessly
    0.14
    åĭĥåĭĥ
    0.12
    пи
    0.11
    fully
    0.10
    ably
    0.10
    assis
    0.10
    æ»ĵ
    0.10
    nel
    0.10
    ÑĤан
    0.10
    bones
    0.09
    Activations Density 0.010%

    No Known Activations