© 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. 12108
    Prev
    Next
    INDEX
    Explanations

    short alphanumeric strings

    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
    Not in Any Lists

    No Comments

    Negative Logits
    dings
    -0.11
    .pref
    -0.11
    sst
    -0.10
    agram
    -0.09
     revers
    -0.09
    FML
    -0.09
    çıĢ
    -0.09
    ardless
    -0.09
    XMLLoader
    -0.09
    å°ıæŶåīį
    -0.09
    POSITIVE LOGITS
    说æľį
    0.08
    å½ĵä¹ĭæĹłæĦ§
    0.08
    éĵ°
    0.08
    å¤ĩåıĹ
    0.08
    ä¸ĭ乡
    0.08
    ä¿Ł
    0.07
    缴å±ŀ
    0.07
     Roch
    0.07
    åħīè¾ī
    0.07
    èº
    0.07
    Activations Density 0.260%

    No Known Activations