© 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. 32293
    Prev
    Next
    INDEX
    Explanations

    Catalan and Scala

    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
    à¹Ĥà¸Ħ
    -0.09
     Ames
    -0.09
     div
    -0.09
    å¾·å·ŀ
    -0.09
    çļĩå¸Ŀ
    -0.08
    horse
    -0.08
     Stout
    -0.08
     Brady
    -0.08
    åIJĦè¡Į
    -0.08
    akt
    -0.08
    POSITIVE LOGITS
     Catalan
    0.12
    æ¹ĺ
    0.11
    æ´£
    0.11
    æ¹ĺæ½Ń
    0.10
     Barcelona
    0.10
    æºĩ
    0.10
    èŁł
    0.10
    cé
    0.09
     Catalonia
    0.09
    æ¹ĸåįĹçľģ
    0.09
    Activations Density 0.142%

    No Known Activations