© 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. 8982
    Prev
    Next
    INDEX
    Explanations

    unpopular / unpleasant topics

    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
    ç»Ī身
    -0.09
    åı£å¤´
    -0.09
    lek
    -0.09
    å°±ä¸įèĥ½
    -0.09
     unintention
    -0.09
     Undo
    -0.08
    åĿĿ
    -0.08
    åĿł
    -0.08
    æİ¥
    -0.08
    åı£æ°Ķ
    -0.08
    POSITIVE LOGITS
     unpopular
    0.15
    ä¸ij
    0.12
    å¾Ĺ罪
    0.11
     unpleasant
    0.11
    æĬ½
    0.10
    硬
    0.10
    å¿ħè¦ģ
    0.10
    é»ijæļĹ
    0.10
    ebra
    0.10
    çĹĽèĭ¦
    0.10
    Activations Density 0.062%

    No Known Activations