© 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. 34150
    Prev
    Next
    INDEX
    Explanations

    interesting articles, opinions, or quotes

    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
    ç¡®åĪĩ
    -0.10
    æł¹æľ¬æ²¡æľī
    -0.09
    èĦIJ
    -0.08
    оÑĢа
    -0.08
    è¡Įèµ°
    -0.08
    åıªè¦ģ
    -0.08
    建档ç«ĭåį¡
    -0.08
    å®Ħ
    -0.08
    çľĦ
    -0.08
    ä¸ĢçĤ¹åĦ¿
    -0.08
    POSITIVE LOGITS
    读åIJİ
    0.15
    è¿Ļç¯ĩ
    0.10
    çľĭå®Į
    0.09
    ä¸īçĤ¹
    0.09
    åħ¨æĸĩ
    0.09
    åIJ¬å®Į
    0.09
    åĢ¼å¾Ĺä¸Ģ
    0.09
    çħ½
    0.09
    è¦ģçĤ¹
    0.09
    èªī
    0.09
    Activations Density 0.275%

    No Known Activations