© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33120
    Prev
    Next
    INDEX
    Explanations

    kinds of numbers

    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
     Morton
    -0.09
    elu
    -0.09
    SES
    -0.09
     Polo
    -0.09
     Mold
    -0.09
    illions
    -0.08
    woo
    -0.08
     займ
    -0.08
    -Nov
    -0.08
    é«ĺçŃī
    -0.08
    POSITIVE LOGITS
    çļĦéĤ£ç§į
    0.09
     kinds
    0.09
    顺便
    0.08
     dozen
    0.08
    å¼Ģæľº
    0.08
    大åݦ
    0.08
    ä¸ĥæĺŁ
    0.08
    èī°
    0.08
     sorts
    0.08
    cms
    0.08
    Activations Density 0.171%

    No Known Activations