© 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. 1639
    Prev
    Next
    INDEX
    Explanations

    communication types

    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
    åŀ£
    -0.13
    禺
    -0.10
    åħ¬ç¤º
    -0.09
    åŁºåĩĨ
    -0.09
    oses
    -0.09
    äºĶæĺŁ
    -0.09
    å¤ĸéĿ¢
    -0.09
    _LOADED
    -0.08
    éĿ¢çĽ®
    -0.08
    orc
    -0.08
    POSITIVE LOGITS
    åĴĮæĶ¯æĮģ
    0.08
    æĢ§çļĦ
    0.08
    agrid
    0.08
     cle
    0.08
    æĦıè§ģ
    0.08
    finder
    0.07
    rus
    0.07
    ÙĬÙĩ
    0.07
     forwards
    0.07
    并åIJij
    0.07
    Activations Density 0.141%

    No Known Activations