© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29905
    Prev
    Next
    INDEX
    Explanations

    indulging or indulgence

    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
    çī¢åĽº
    -0.09
    uras
    -0.09
    ching
    -0.09
    ched
    -0.08
    oul
    -0.08
    ç¾¹
    -0.08
    apel
    -0.08
    icos
    -0.08
    ubes
    -0.08
    ä¸įåĥı
    -0.08
    POSITIVE LOGITS
    æģ£
    0.10
    äºĨåįĬ天
    0.10
    èĢĨ
    0.10
    åĴĮæĶ¯æĮģ
    0.10
    ·
    0.10
    äºĨå¾Īä¹ħ
    0.10
    емÑģÑı
    0.10
    enti
    0.10
    æĵİ
    0.09
    æĪIJè´¥
    0.09
    Activations Density 0.003%

    No Known Activations