© 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. 51786
    Prev
    Next
    INDEX
    Explanations

    ensure that

    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
    干线
    -0.10
    usz
    -0.09
    毫ä¸įçĬ¹è±«
    -0.09
    åĨī
    -0.09
     Fax
    -0.08
    说çļĦæĺ¯
    -0.08
    hip
    -0.08
    æ»ĭåħ»
    -0.08
    åĨ³çŃĸ
    -0.08
    ols
    -0.08
    POSITIVE LOGITS
     ÑĢабоÑĤ
    0.09
    æĤ¬æµ®
    0.09
    裳
    0.09
    åĥĸ
    0.08
    åŀĵ
    0.08
    æľĪèĸª
    0.08
     pena
    0.08
    .End
    0.08
    Ñıм
    0.08
    maker
    0.08
    Activations Density 0.051%

    No Known Activations