© 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. 20708
    Prev
    Next
    INDEX
    Explanations

    mergers and acquisitions

    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
    зов
    -0.11
    ä¹ĥèĩ³
    -0.09
    èĩªä¿¡
    -0.09
    ivot
    -0.09
    arehouse
    -0.09
     McCartney
    -0.09
    -muted
    -0.09
    ocr
    -0.08
    mur
    -0.08
    actors
    -0.08
    POSITIVE LOGITS
    èįĴ
    0.09
    åľ°äº§
    0.09
    浪潮
    0.08
     flaming
    0.08
    town
    0.08
    æ°IJ
    0.08
    ient
    0.08
    人éĢī
    0.08
    akan
    0.08
    çĴľ
    0.08
    Activations Density 0.021%

    No Known Activations