© 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. 51611
    Prev
    Next
    INDEX
    Explanations

    PM and related abbreviations

    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
    èģĶ缣
    -0.10
    ä½ıåĿĢ
    -0.10
    ä¸ĢåŃĹ
    -0.09
    æĺŃ
    -0.09
    æįĨç»ij
    -0.08
    lotte
    -0.08
    lename
    -0.08
    åħ¥åĽŃ
    -0.08
    温室
    -0.08
    .setDefault
    -0.08
    POSITIVE LOGITS
    upid
    0.09
    omic
    0.09
    è´±
    0.09
    çĤ¼
    0.09
    çŃĴ
    0.08
    Ars
    0.08
    æŃ£å¥½
    0.08
    è¿Ļä¹Īåģļ
    0.08
     unf
    0.08
    urg
    0.08
    Activations Density 0.029%

    No Known Activations