© 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. 20157
    Prev
    Next
    INDEX
    Explanations

    copyright and license notices

    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
    ä»Ģä¹Īåij¢
    -0.09
    ãģĤãģ£ãģŁ
    -0.09
    äºĽ
    -0.08
    éĤ£æł·çļĦ
    -0.08
    ely
    -0.08
    峪
    -0.08
    oder
    -0.08
    orig
    -0.08
    swith
    -0.08
    asz
    -0.08
    POSITIVE LOGITS
    à¸ģระà¸Ĺ
    0.10
    çī¹åĪ«æĺ¯
    0.10
    nbsp
    0.10
    halb
    0.10
    äºĮæĺ¯
    0.09
    king
    0.09
    /or
    0.09
    irs
    0.09
    åħ¶æ¬¡æĺ¯
    0.09
    åĬªåĬĽ
    0.09
    Activations Density 0.358%

    No Known Activations