© 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. 9165
    Prev
    Next
    INDEX
    Explanations

    bickering, quarrelling, disagreement, fight

    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
    è¡Įæĥħ
    -0.10
    achat
    -0.10
    tı
    -0.09
    èĦī
    -0.09
    GroupName
    -0.09
    Newsletter
    -0.09
     ÑħÑĢ
    -0.08
    .getActive
    -0.08
     punch
    -0.08
     dangers
    -0.08
    POSITIVE LOGITS
    äºī
    0.12
    纷
    0.10
    éĺĤ
    0.10
    çĪŃ
    0.10
    äºī夺
    0.10
    æĦıè§ģ
    0.10
    åķ¼
    0.10
    äºī缸
    0.10
    äºīåIJµ
    0.10
    åĴĮçĿ¦
    0.09
    Activations Density 0.045%

    No Known Activations