© 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. 23514
    Prev
    Next
    INDEX
    Explanations

    already known or seen

    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
    çĻĸ
    -0.09
    ä¸Ģçĵ¶
    -0.09
    åĽ½æĥħ
    -0.09
    StyleSheet
    -0.09
    ç²¾åĩĨæī¶è´«
    -0.09
    èµĬ
    -0.09
    ä¸ĢçĽ´æ²¡æľī
    -0.08
    åıĺæĪIJäºĨ
    -0.08
     clearfix
    -0.08
    å¾Ĺ罪
    -0.08
    POSITIVE LOGITS
    æĹ©å·²
    0.12
    _ALREADY
    0.10
    饱åĴĮ
    0.10
    æľīè¿ĩ
    0.10
    éĥ½å·²ç»ı
    0.10
    说è¿ĩ
    0.10
    å·²æľī
    0.10
     already
    0.09
    å·²ç»ıåľ¨
    0.09
    already
    0.09
    Activations Density 0.128%

    No Known Activations