© 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. 51772
    Prev
    Next
    INDEX
    Explanations

    continues or persists

    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
    æĬ¬
    -0.10
    å·©
    -0.09
    ancellable
    -0.09
    éľ¹
    -0.09
    篱
    -0.09
    æĿ¥å®¾
    -0.09
    .shtml
    -0.08
    èĩªè¡Į车
    -0.08
    PK
    -0.08
    æĮijåīĶ
    -0.08
    POSITIVE LOGITS
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    0.13
    ä¾Ŀæŧ
    0.09
    åİŁæľīçļĦ
    0.09
    redi
    0.08
    prox
    0.08
    ral
    0.08
    åİŁæľī
    0.08
     ob
    0.08
    è¿ĺæĺ¯ä¼ļ
    0.08
    çħ§æł·
    0.08
    Activations Density 0.047%

    No Known Activations