© 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. 20643
    Prev
    Next
    INDEX
    Explanations

    arbitrary things, functions, states, strings, ports

    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
    opath
    -0.10
    bru
    -0.10
    OptionsResolver
    -0.09
    åıĺå½¢
    -0.09
    _reordered
    -0.09
    oriously
    -0.09
    æ¦Ń
    -0.09
    enan
    -0.09
    çī¹æľīçļĦ
    -0.09
    arah
    -0.09
    POSITIVE LOGITS
    /random
    0.10
    æĢ§å¼º
    0.10
     arbitrary
    0.10
     Arbitrary
    0.09
     assort
    0.09
     assortment
    0.08
     chosen
    0.08
    åĹª
    0.08
    å¸®ä½ł
    0.08
    åıįæŃ£
    0.08
    Activations Density 0.021%

    No Known Activations