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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37333
    Prev
    Next
    INDEX
    Explanations

    blankets and carpets

    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
    åķī
    -0.11
    acious
    -0.09
    ally
    -0.09
    ãĥ£
    -0.09
    obi
    -0.09
    å¥łåŁº
    -0.09
    irty
    -0.09
     اÙĦÙĥبÙĬر
    -0.09
    éħIJ
    -0.09
    ignal
    -0.08
    POSITIVE LOGITS
    ãģĮãĤī
    0.11
     Ñģобой
    0.11
    coverage
    0.10
    edly
    0.10
    ï¸ı
    0.09
    íķij
    0.09
    ç»Ń
    0.09
    ieri
    0.09
    edin
    0.09
    миÑĢ
    0.09
    Activations Density 0.003%

    No Known Activations