© 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. 34897
    Prev
    Next
    INDEX
    Explanations

    different from

    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
    å¦ĤæĦı
    -0.09
    åĪ»
    -0.08
     both
    -0.08
    åѤç«ĭ
    -0.08
    å¾Ĺèµ·
    -0.08
    æ³ī
    -0.08
    çīµ
    -0.08
     вли
    -0.08
    欹
    -0.08
     Webb
    -0.08
    POSITIVE LOGITS
    åĥı个
    0.11
    åĮºåĪ«
    0.11
    ç§ĺ书éķ¿
    0.10
    SMART
    0.10
    å°±åĥıæĺ¯
    0.10
    çĻ½éĽª
    0.09
    icle
    0.09
    åīįæĸ¹
    0.09
    èĭ«
    0.09
    å°±æĺ¯ä¸Ģ个
    0.09
    Activations Density 0.042%

    No Known Activations