© 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. 47437
    Prev
    Next
    INDEX
    Explanations

    jamming or jamison

    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
    çĦ¶
    -0.10
    hood
    -0.10
    è¯ŀ
    -0.10
     Ames
    -0.10
    inal
    -0.09
    ium
    -0.09
    ity
    -0.09
    iosis
    -0.09
    orate
    -0.08
    念
    -0.08
    POSITIVE LOGITS
    WithOptions
    0.11
     jams
    0.10
    خص
    0.10
    olin
    0.09
    jam
    0.09
     jam
    0.09
    .TRAILING
    0.09
    /vnd
    0.09
    ®
    0.09
    eries
    0.09
    Activations Density 0.005%

    No Known Activations