© 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. 9029
    Prev
    Next
    INDEX
    Explanations

    web pages and files

    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
    人éĢī
    -0.09
    èĥĮçĿĢ
    -0.09
    æ¼ī
    -0.09
    éĢīåĩº
    -0.08
    å¿ĥçģµ
    -0.08
    ä¸ŃåİŁ
    -0.08
    áĥ¥
    -0.08
    èĥĮä¸Ĭ
    -0.08
    åĬ¨çĶŁæĪIJ
    -0.08
    æ²īéĩį
    -0.08
    POSITIVE LOGITS
    å®īå®ģ
    0.08
    éªĦ
    0.08
    kip
    0.08
    itore
    0.08
    WER
    0.08
    ä¸Ģç»ı
    0.08
     \%
    0.08
    è¿ŀè½½
    0.08
    åħ¨çIJĥ
    0.08
     Svens
    0.07
    Activations Density 0.009%

    No Known Activations