© 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. 53180
    Prev
    Next
    INDEX
    Explanations

    analyze

    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
    eld
    -0.11
    ITIONAL
    -0.10
    aney
    -0.09
    æ³Ĭ
    -0.09
    XP
    -0.09
     notion
    -0.09
    åıijæĺİ
    -0.09
     Fancy
    -0.09
    дÑĥÑĤ
    -0.08
    atu
    -0.08
    POSITIVE LOGITS
    åĪĨæŀIJ
    0.14
    çłĶåĪ¤
    0.13
    æŀIJ
    0.13
    -analysis
    0.11
     анализ
    0.10
     analysis
    0.10
    .analysis
    0.10
    analysis
    0.09
    analyze
    0.09
     analys
    0.09
    Activations Density 0.185%

    No Known Activations