© 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. 32816
    Prev
    Next
    INDEX
    Explanations

    resolving issues

    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
    çĨ¨
    -0.09
    äºĭæķħåıijçĶŁ
    -0.09
    avern
    -0.09
    æIJŀ好
    -0.09
    mint
    -0.09
    reiben
    -0.09
    æĬ±åĽ¢
    -0.09
    \brief
    -0.09
    .Sync
    -0.08
    tı
    -0.08
    POSITIVE LOGITS
    ä¹ĭéģĵ
    0.14
    ä¸įäºĨ
    0.12
     rÃłng
    0.11
    odash
    0.09
    ponder
    0.09
    åı¯æĥ³
    0.09
    没æľīæĥ³åĪ°
    0.08
    åĴĸ
    0.08
    ksi
    0.08
     Rub
    0.08
    Activations Density 0.173%

    No Known Activations