© 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. 30477
    Prev
    Next
    INDEX
    Explanations

    traditional French

    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
    pekt
    -0.08
    称ä¹ĭ
    -0.08
    벤
    -0.08
    èµĦ产éĩįç»Ħ
    -0.08
    循
    -0.08
    nex
    -0.08
    averse
    -0.08
    èľķ
    -0.08
    è´Ŀå°Ķ
    -0.08
     recom
    -0.07
    POSITIVE LOGITS
    æł·å¼ı
    0.12
    è¿Ļç±»
    0.11
    åĪ¶ä½ľ
    0.10
    æīĭæ³ķ
    0.10
    é£İæł¼
    0.10
    å·¥èīº
    0.10
    æѤ类
    0.09
    å·§
    0.09
    è¿Ļ个è¡Įä¸ļ
    0.09
    æĬĢæ³ķ
    0.09
    Activations Density 0.086%

    No Known Activations