© 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. 33661
    Prev
    Next
    INDEX
    Explanations

    heels and parts of shoes

    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
    饶
    -0.10
    илÑģÑı
    -0.09
    илиÑģÑĮ
    -0.09
    esco
    -0.09
    ÃŃs
    -0.09
    ãģıãĤĮ
    -0.09
    hydro
    -0.08
     pháºŃn
    -0.08
    hip
    -0.08
    illis
    -0.08
    POSITIVE LOGITS
    lessly
    0.09
    inders
    0.09
    èĢģçĪ¸
    0.09
    zap
    0.09
    laces
    0.09
    лов
    0.09
    æĪijåİ»
    0.09
     desn
    0.09
    ÙĤر
    0.09
    ⼦
    0.08
    Activations Density 0.006%

    No Known Activations