© 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. 50749
    Prev
    Next
    INDEX
    Explanations

    due to

    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
    主æĦı
    -0.10
    åŃĺ
    -0.09
    åĬ«
    -0.09
    creative
    -0.09
    GRES
    -0.09
    åı°
    -0.08
    hower
    -0.08
    åĢŁéī´
    -0.08
     اÙĦÙģÙĦ
    -0.08
    çĤ¹åĩ»æŁ¥çľĭ
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹ĪåİŁåĽł
    0.11
    éĢłæĪIJçļĦ
    0.10
    å¼ķèµ·çļĦ
    0.10
    /in
    0.10
     Boss
    0.09
    ssel
    0.09
    è¿ĩåİ»çļĦ
    0.08
    æĹłæĥħ
    0.08
    è¿Ļ个人
    0.08
     caused
    0.08
    Activations Density 0.179%

    No Known Activations