© 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. 20081
    Prev
    Next
    INDEX
    Explanations

    brand names and their products/services

    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
    ä¸Ńéĵģ
    -0.10
    åħĪéĶĭ
    -0.09
    æ¡¥
    -0.08
    æĴij
    -0.08
    山谷
    -0.08
    ä¸ŃåĽ½åĽ½éĻħ
    -0.08
    å©Ĩå©Ĩ
    -0.08
     pont
    -0.08
     whom
    -0.08
     fem
    -0.08
    POSITIVE LOGITS
    çĭ¬æľīçļĦ
    0.11
    çī¹æľīçļĦ
    0.11
    ä¸İåħ¶
    0.10
     Macy
    0.10
    ä¼ĺåĬ¿
    0.09
    SelectionMode
    0.09
    /effects
    0.09
    åľ¨ç½ij绾
    0.09
    åľ¨åħ¨çIJĥ
    0.09
    -owned
    0.09
    Activations Density 0.142%

    No Known Activations