© 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. 50429
    Prev
    Next
    INDEX
    Explanations

    negative adjectives

    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
    以便
    -0.09
    å¾ģæ±ĤæĦıè§ģ
    -0.09
    ä½ľåĵģ
    -0.09
    Than
    -0.08
    åģļæ³ķ
    -0.08
    æĭĽåij¼
    -0.08
     kart
    -0.08
    森
    -0.08
    以åıĬ
    -0.08
     Weiner
    -0.08
    POSITIVE LOGITS
    çĶļèĩ³æĺ¯
    0.11
    æķ´ä¸ªäºº
    0.10
    лей
    0.09
    æľ¬èº«
    0.09
    置身
    0.09
    çĶļèĩ³
    0.09
    æķ´è½¦
    0.09
    çIJĨä¼ļ
    0.09
    ä¸ĢæŶ
    0.08
    èĹģ
    0.08
    Activations Density 0.082%

    No Known Activations