© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20340
    Prev
    Next
    INDEX
    Explanations

    and conjunction

    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
    ä¸įåģľçļĦ
    -0.09
    æī¿æĭħ责任
    -0.08
    ä¸įæĸŃçļĦ
    -0.08
    ahren
    -0.08
    resses
    -0.08
    æħ¢æħ¢çļĦ
    -0.08
    çĦļ
    -0.08
    æ·±åĪ»çļĦ
    -0.08
    æľīæķĪçļĦ
    -0.08
     ден
    -0.08
    POSITIVE LOGITS
    ãģĨãģ¡
    0.10
    éĺĨ
    0.09
    uate
    0.09
    åīįæıIJæĺ¯
    0.09
    zure
    0.09
    oload
    0.08
    åį±å®³
    0.08
    åıĮèĦļ
    0.08
    åĴİ
    0.08
    麻çĥ¦
    0.08
    Activations Density 0.168%

    No Known Activations