© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 55836
    Prev
    Next
    INDEX
    Explanations

    national anthem and flags

    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
    çħ§
    -0.10
    éªIJ
    -0.09
    ì§ĵ
    -0.08
     reap
    -0.08
    éĻª
    -0.08
    eson
    -0.08
    å¹²çĩ¥
    -0.08
    åĢ¾åIJ¬
    -0.08
    æĶ¾å¼ĥäºĨ
    -0.08
    illas
    -0.07
    POSITIVE LOGITS
    çĪ±åĽ½ä¸»ä¹ī
    0.25
    çĪ±åĽ½
    0.25
     patriotic
    0.21
     patriotism
    0.20
    åĽ½æĹĹ
    0.20
     patriot
    0.17
     Patriot
    0.17
    åĽ½åľŁ
    0.17
    ç¥ĸåĽ½
    0.16
    åĽ½æĥħ
    0.15
    Activations Density 0.096%

    No Known Activations