© 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. 35930
    Prev
    Next
    INDEX
    Explanations

    research interests and focus

    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
    quer
    -0.09
    dess
    -0.09
     dess
    -0.09
    åIJ¸
    -0.09
    etros
    -0.08
     Dagger
    -0.08
    æĺ¯æĪij们
    -0.08
    0
    -0.08
    汪
    -0.07
    ees
    -0.07
    POSITIVE LOGITS
    主è¦ģä»İäºĭ
    0.12
    åĪĨ管
    0.11
    èĩ´åĬĽ
    0.10
    躬
    0.10
    æ´Ľåħĭ
    0.10
    æĶ¯éĺŁ
    0.10
    é¢ĨåŁŁ
    0.10
    éłĺåŁŁ
    0.10
     ÙĪاÙĦا
    0.10
    以åĨħ
    0.10
    Activations Density 0.095%

    No Known Activations