© 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. 37036
    Prev
    Next
    INDEX
    Explanations

    religious organizations and titles

    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
    èªĵ
    -0.10
    çĴ§
    -0.09
    æ¸ĹéĢı
    -0.09
    æݸ
    -0.09
    æµģ失
    -0.09
    说èĩªå·±
    -0.09
    æ¸ħæī«
    -0.09
    idas
    -0.09
    ç©Ĺ
    -0.09
    çĵ®
    -0.09
    POSITIVE LOGITS
     Cardinal
    0.10
     Catholic
    0.10
    次
    0.10
    æ¼²
    0.08
     Catholics
    0.08
    èĭıå·ŀ
    0.08
    buzz
    0.08
    aec
    0.08
    çģµ
    0.08
     miá»ģn
    0.08
    Activations Density 0.126%

    No Known Activations