© 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. 1578
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    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
    cco
    -0.09
    lessly
    -0.08
    Unnamed
    -0.08
    cob
    -0.08
     Cav
    -0.07
    STE
    -0.07
     automáticamente
    -0.07
    nbsp
    -0.07
     POD
    -0.07
    æĪ¢
    -0.07
    POSITIVE LOGITS
    rega
    0.09
    urette
    0.09
    iest
    0.09
    人çĶŁçļĦ
    0.09
    eral
    0.09
    ularity
    0.09
    eros
    0.09
     اÙĦÙĨÙģس
    0.08
    ure
    0.08
    ega
    0.08
    Activations Density 0.400%

    No Known Activations