© 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. 10680
    Prev
    Next
    INDEX
    Explanations

    newsletters, accounts, lists, websites, sentences

    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
    _fwd
    -0.10
    éĤ£åĦ¿
    -0.08
    åĺĽ
    -0.08
    红è±Ĩ
    -0.08
    esters
    -0.08
    sembl
    -0.08
    uras
    -0.08
    annies
    -0.08
    uars
    -0.08
    綦
    -0.08
    POSITIVE LOGITS
    ä¸įåIJĮçļĦ
    0.11
    å¥ı
    0.11
    ito
    0.10
    åIJĦåĮº
    0.10
    åIJĦ个
    0.10
    殿
    0.09
    ä¸įåIJĮç±»åŀĭ
    0.09
    ä¸įåIJĮ
    0.09
     اÙĦÙħختÙĦÙģØ©
    0.09
    éĺĤ
    0.09
    Activations Density 0.582%

    No Known Activations