© 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. 51386
    Prev
    Next
    INDEX
    Explanations

    example, say, let's

    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
    endale
    -0.10
    å¼ķãģ£
    -0.10
    endDate
    -0.09
    xis
    -0.09
    示èĮĥ
    -0.09
    endo
    -0.09
    ãģĿãĤĮãģ§ãĤĤ
    -0.09
    TERM
    -0.09
    èħķ
    -0.09
    .setTag
    -0.09
    POSITIVE LOGITS
    说æĺ¯
    0.11
    åı¯ä»¥è¯´æĺ¯
    0.10
    æĥ³æĥ³
    0.10
    åı¯ä»¥è¯´
    0.09
    çŁ¾
    0.09
    cs
    0.09
    说å®ŀè¯Ŀ
    0.09
     dare
    0.08
    icial
    0.08
    vir
    0.08
    Activations Density 0.153%

    No Known Activations