© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7168
    Prev
    Next
    INDEX
    Explanations

    after all

    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
    å¯Ł
    -0.09
    ifier
    -0.09
    IFY
    -0.09
    æķĻèĤ²æķĻåѦ
    -0.09
    edom
    -0.09
    ification
    -0.08
    ifiers
    -0.08
    éľı
    -0.08
    ality
    -0.08
     Hartford
    -0.08
    POSITIVE LOGITS
    æ¯ķç«Ł
    0.12
    wards
    0.10
    æ¯ķç«Łæĺ¯
    0.10
    èĻij
    0.09
    æĹłäºº
    0.09
    çķ¢ç«Ł
    0.09
    èŀºä¸Ŀ
    0.09
    çħ§é¡¾
    0.09
    å®ĥæĺ¯
    0.08
    社ä¼ļ责任
    0.08
    Activations Density 0.002%

    No Known Activations