© 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. 10764
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating location or time

    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
    åıijçĶŁåľ¨
    -0.12
    åľ¨çĶŁæ´»ä¸Ń
    -0.11
    åĩºçİ°åľ¨
    -0.10
    çĶŁæ´»åľ¨
    -0.10
    éĽĨä¸Ńåľ¨
    -0.10
    åŃĺåľ¨äºİ
    -0.10
    åľ¨éĩĮéĿ¢
    -0.09
    åľ¨è·¯ä¸Ĭ
    -0.09
    åľ¨å¸Ĥåľºä¸Ĭ
    -0.08
     Ñģобой
    -0.08
    POSITIVE LOGITS
    çŃīåľ°
    0.16
    åľ°åĮºçļĦ
    0.12
    -area
    0.10
    -based
    0.10
    è¡Ĺ头
    0.10
    èijĹåIJįçļĦ
    0.10
    æľīåIJįçļĦ
    0.10
    è¿Ļä¸ªåľ°æĸ¹
    0.10
    åľ°æłĩ
    0.10
    éĽ¾éľ¾
    0.09
    Activations Density 0.503%

    No Known Activations