© 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. 60614
    Prev
    Next
    INDEX
    Explanations

    files transferring data

    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
    ä¸ĩæĪ·
    -0.10
    çµ®
    -0.10
    çŀ½
    -0.10
    å¾ĩ
    -0.09
    æħµ
    -0.09
    èĩªæĿ¥
    -0.09
    iji
    -0.09
    prite
    -0.09
    azine
    -0.09
    è´µ
    -0.09
    POSITIVE LOGITS
     transfer
    0.17
    转移
    0.16
     Transfer
    0.15
    转移åĪ°
    0.15
    transfer
    0.14
    Transfer
    0.14
     transfers
    0.13
     transferred
    0.13
    TRANSFER
    0.12
    .transfer
    0.12
    Activations Density 0.121%

    No Known Activations