© 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. 62832
    Prev
    Next
    INDEX
    Explanations

    enjoy activities

    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
    éĹľä¿Ĥ
    -0.10
    /cop
    -0.09
    åIJįæł¡
    -0.09
    ä¼Ĭæĭī
    -0.09
    éİı
    -0.09
     perg
    -0.09
    ä¼łè¨Ģ
    -0.09
    ç»ı常
    -0.09
    åħ³ç³»
    -0.09
    人为
    -0.09
    POSITIVE LOGITS
    享åıĹ
    0.13
    享
    0.11
    享åıĹåĪ°
    0.11
    ä¹IJ趣
    0.10
    åħħ
    0.10
    驾é©Ń
    0.08
     guilt
    0.08
    çĤ¹ç¼Ģ
    0.08
    ä¸Ģåľº
    0.08
    é¢Ĩçķ¥
    0.08
    Activations Density 0.039%

    No Known Activations