© 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. 20284
    Prev
    Next
    INDEX
    Explanations

    lately followed by current activity or state

    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
    ãģĦãģ¾
    -0.10
    ä¸Ģè¾ĪåŃIJ
    -0.10
    å½ĵä»Ĭ
    -0.09
    elman
    -0.09
    æĭľ
    -0.09
    è¿Ļä¹Ī说
    -0.09
    å½ĵæŶçļĦ
    -0.08
    oad
    -0.08
    er
    -0.08
    æĭīçĿĢ
    -0.08
    POSITIVE LOGITS
    chy
    0.10
    ãģĬãĤĬ
    0.09
    abouts
    0.09
    迹象
    0.09
    tempt
    0.09
    以ä¾Ĩ
    0.09
    ork
    0.09
    antlr
    0.08
    NewLabel
    0.08
    iper
    0.08
    Activations Density 0.011%

    No Known Activations