© 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. 29523
    Prev
    Next
    INDEX
    Explanations

    get back into shape

    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
    éļľ
    -0.09
    修为
    -0.09
    -word
    -0.09
    terr
    -0.09
     UClass
    -0.09
    çħ²
    -0.08
    èįĶæŀĿ
    -0.08
    edith
    -0.08
    eted
    -0.08
    .getClassName
    -0.08
    POSITIVE LOGITS
    éĤ£ç§į
    0.11
     Cav
    0.09
    欢è¿İ大家
    0.09
    éĢĤåºĶ
    0.09
     cavity
    0.09
     cav
    0.08
    欢è¿İ
    0.08
    atus
    0.08
    è¿Ļä¹Ī大
    0.08
    就被
    0.08
    Activations Density 0.034%

    No Known Activations