© 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. 33741
    Prev
    Next
    INDEX
    Explanations

    decoration or accessory

    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
    éĢģåİ»
    -0.09
    缴éĶĢ
    -0.08
    æīĢå¾Ĺç¨İ
    -0.08
    颧
    -0.08
    rale
    -0.08
    çģ°
    -0.08
     Tanner
    -0.08
    -ish
    -0.08
    社交
    -0.08
    é»Ħæĺı
    -0.08
    POSITIVE LOGITS
    饰
    0.19
    修饰
    0.15
    飾
    0.15
    ç»ĨèĬĤ
    0.15
    è£ħ饰
    0.14
    çĤ¹ç¼Ģ
    0.14
    饰åĵģ
    0.12
    éħį件
    0.11
    -decoration
    0.10
    è¢ĸ
    0.10
    Activations Density 0.097%

    No Known Activations