© 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. 37299
    Prev
    Next
    INDEX
    Explanations

    property damage

    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
    è¿Ļä¹Īåģļ
    -0.10
    å«©
    -0.09
    å¼ı
    -0.09
    emet
    -0.09
    èĭıå®ģ
    -0.09
    éħ
    -0.09
    -speaking
    -0.08
    ä¸Ģ个éĹ®é¢ĺ
    -0.08
    åĩłæ¬¡
    -0.08
    ä¸ĢåĽŀäºĭ
    -0.08
    POSITIVE LOGITS
    财产
    0.15
    è´¢çī©
    0.13
    endi
    0.11
    大ä¼Ĺ
    0.10
    IMS
    0.10
    RESS
    0.10
     property
    0.10
    財
    0.09
    设æĸ½
    0.09
    è´¢å¯Į
    0.09
    Activations Density 0.180%

    No Known Activations