© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36979
    Prev
    Next
    INDEX
    Explanations

    industry

    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
    çĶŁæ´»
    -0.10
    æĪĸå¤ļ
    -0.09
    èĩ³ä¸Ĭ
    -0.09
    æĹ¥å¸¸çĶŁæ´»
    -0.09
    å®īå±ħ
    -0.09
    绩æķĪ
    -0.09
    人çĶŁ
    -0.09
    çĶŁæ´»è´¨éĩı
    -0.09
    为ä¼ģä¸ļ
    -0.08
    æľĽ
    -0.08
    POSITIVE LOGITS
    è¿Ļ个è¡Įä¸ļ
    0.24
    è¡Įä¸ļåĨħ
    0.21
    ä»İä¸ļèĢħ
    0.20
    è¡Įä¸ļ
    0.20
    è¡Įä¸ļçļĦ
    0.20
     industry
    0.19
    è¡Įä¸ļä¸Ń
    0.19
    ä»İä¸ļ人åijĺ
    0.19
    industry
    0.17
    è¡Įä¸ļåıijå±ķ
    0.17
    Activations Density 0.182%

    No Known Activations