© 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. 20523
    Prev
    Next
    INDEX
    Explanations

    circumstances and conditions

    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
    æľªæĪIJ
    -0.10
    å¿ĥæĢĿ
    -0.09
    éĤ£å¤©
    -0.09
    å¾Ģä¸ĭ
    -0.09
    segue
    -0.09
    som
    -0.09
    çĵľ
    -0.08
    ä½ĵä¼ļåĪ°
    -0.08
    adden
    -0.08
     Mercer
    -0.08
    POSITIVE LOGITS
    æĿ¡ä»¶ä¸ĭ
    0.14
    æĥħåĨµä¸ĭ
    0.13
     circumstances
    0.12
     conditions
    0.11
    .conditions
    0.11
    conditions
    0.10
    _conditions
    0.10
    Conditions
    0.10
     situations
    0.10
     occasions
    0.10
    Activations Density 0.107%

    No Known Activations