© 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. 38051
    Prev
    Next
    INDEX
    Explanations

    desire and wanting

    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
    ober
    -0.10
    çĿĢçľ¼
    -0.09
    åĽŀ头
    -0.09
    åĪ°ä½į
    -0.09
    uis
    -0.08
    adel
    -0.08
    ellan
    -0.08
    reo
    -0.08
    eced
    -0.08
    æłª
    -0.08
    POSITIVE LOGITS
    强çĥĪçļĦ
    0.14
    强çĥĪ
    0.12
    æĬ¥å¤į
    0.12
    åIJijå¾Ģ
    0.10
    æĦ¿æľĽ
    0.10
     desire
    0.10
    æĹºçĽĽ
    0.10
    寻æ±Ĥ
    0.10
     wanting
    0.10
    want
    0.10
    Activations Density 0.024%

    No Known Activations