© 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. 8310
    Prev
    Next
    INDEX
    Explanations

    drive business growth

    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
     велик
    -0.11
    ä¾Ī
    -0.10
    åĽ¾æłĩ
    -0.10
    ä¹¡åľŁ
    -0.10
    ç³Ł
    -0.09
    çıł
    -0.09
    å¸ĤéĿ¢ä¸Ĭ
    -0.09
    heed
    -0.09
    åĽ½éĻħå¸Ĥåľº
    -0.09
    å¸Ĥåľºç«ŀäºī
    -0.09
    POSITIVE LOGITS
    åı¬
    0.12
     конкÑĢеÑĤ
    0.10
    æĶ¶åħ¥
    0.09
    òng
    0.09
    带æĿ¥
    0.09
    inds
    0.09
    æĭĽçĶŁ
    0.09
    ions
    0.09
    ey
    0.09
    enn
    0.08
    Activations Density 0.040%

    No Known Activations