© 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. 58384
    Prev
    Next
    INDEX
    Explanations

    we, they, or you context

    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
    éĤ£äºº
    -0.09
    åĪĨãģĭãĤĭ
    -0.08
    éĨĴäºĨ
    -0.08
    æ¿
    -0.08
    满满
    -0.08
    æĴµ
    -0.08
    çļĦéĤ£ç§į
    -0.08
    æĪijè¿ĺ
    -0.08
    outs
    -0.08
    åŁºç¡Ģä¸Ĭ
    -0.07
    POSITIVE LOGITS
    enne
    0.10
     наиболее
    0.09
    .Authorization
    0.09
    arus
    0.09
    æīįæĺ¯çľŁæŃ£
    0.08
    골
    0.08
    yor
    0.08
    liner
    0.08
    åĴĮæľįåĬ¡
    0.08
    лин
    0.08
    Activations Density 0.094%

    No Known Activations