© 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. 3857
    Prev
    Next
    INDEX
    Explanations

    outdoor activities, friendliness

    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
    æīĵåĮħ
    -0.09
    AFP
    -0.09
    åĽ·
    -0.09
    alist
    -0.09
    edList
    -0.09
    ully
    -0.09
    æ¸ħæ´Ĺ
    -0.09
    æ´Ĺ澡
    -0.09
     Fam
    -0.08
    ream
    -0.08
    POSITIVE LOGITS
    åįļçī©é¦Ĩ
    0.10
     museums
    0.09
    åħ¬ç«ĭ
    0.09
    é¢Ģ
    0.08
    æ¹ĸæ³Ĭ
    0.08
    çī¯
    0.08
    æľīåºı
    0.08
    精彩çļĦ
    0.08
     ÑĢек
    0.08
    éªĦåĤ²
    0.08
    Activations Density 0.052%

    No Known Activations